diff --git a/python/Cargo.lock b/python/Cargo.lock index d971675f4f..543d12523e 100644 --- a/python/Cargo.lock +++ b/python/Cargo.lock @@ -57,9 +57,9 @@ dependencies = [ [[package]] name = "allocator-api2" -version = "0.2.18" +version = "0.2.21" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "5c6cb57a04249c6480766f7f7cef5467412af1490f8d1e243141daddada3264f" +checksum = "683d7910e743518b0e34f1186f92494becacb047c7b6bf616c96772180fef923" [[package]] name = "android-tzdata" @@ -78,9 +78,9 @@ dependencies = [ [[package]] name = "anyhow" -version = "1.0.92" +version = "1.0.94" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "74f37166d7d48a0284b99dd824694c26119c700b53bf0d1540cdb147dbdaaf13" +checksum = "c1fd03a028ef38ba2276dce7e33fcd6369c158a1bca17946c4b1b701891c1ff7" [[package]] name = "arc-swap" @@ -150,7 +150,7 @@ dependencies = [ "chrono", "chrono-tz", "half", - "hashbrown 0.15.1", + "hashbrown 0.15.2", "num", ] @@ -347,9 +347,9 @@ dependencies = [ [[package]] name = "async-compression" -version = "0.4.17" +version = "0.4.18" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "0cb8f1d480b0ea3783ab015936d2a55c87e219676f0c0b7dec61494043f21857" +checksum = "df895a515f70646414f4b45c0b79082783b80552b373a68283012928df56f522" dependencies = [ "bzip2", "flate2", @@ -393,9 +393,9 @@ dependencies = [ [[package]] name = "async-io" -version = "2.3.4" +version = "2.4.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "444b0228950ee6501b3568d3c93bf1176a1fdbc3b758dcd9475046d30f4dc7e8" +checksum = "43a2b323ccce0a1d90b449fd71f2a06ca7faa7c54c2751f06c9bd851fc061059" dependencies = [ "async-lock", "cfg-if", @@ -438,7 +438,7 @@ checksum = "3b43422f69d8ff38f95f1b2bb76517c91589a924d1559a0e935d7c8ce0274c11" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -481,7 +481,7 @@ checksum = "721cae7de5c34fbb2acd27e21e6d2cf7b886dce0c27388d46c4e6c47ea4318dd" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -513,9 +513,9 @@ checksum = "ace50bade8e6234aa140d9a2f552bbee1db4d353f69b8217bc503490fc1a9f26" [[package]] name = "aws-config" -version = "1.5.9" +version = "1.5.10" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "2d6448cfb224dd6a9b9ac734f58622dd0d4751f3589f3b777345745f46b2eb14" +checksum = "9b49afaa341e8dd8577e1a2200468f98956d6eda50bcf4a53246cc00174ba924" dependencies = [ "aws-credential-types", "aws-runtime", @@ -524,7 +524,7 @@ dependencies = [ "aws-sdk-sts", "aws-smithy-async", "aws-smithy-http", - "aws-smithy-json", + "aws-smithy-json 0.60.7", "aws-smithy-runtime", "aws-smithy-runtime-api", "aws-smithy-types", @@ -555,9 +555,9 @@ dependencies = [ [[package]] name = "aws-runtime" -version = "1.4.3" +version = "1.4.4" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a10d5c055aa540164d9561a0e2e74ad30f0dcf7393c3a92f6733ddf9c5762468" +checksum = "b5ac934720fbb46206292d2c75b57e67acfc56fe7dfd34fb9a02334af08409ea" dependencies = [ "aws-credential-types", "aws-sigv4", @@ -580,15 +580,15 @@ dependencies = [ [[package]] name = "aws-sdk-dynamodb" -version = "1.52.0" +version = "1.55.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "473aa619c2a3581ab00d9000e66a11982f6354d0150797518b8d459c7f9a6b5c" +checksum = "a18e18b3cf6b75c1fcb15e677f6dbd2a6d8dfe4d168e0a36721f7a6167c6c829" dependencies = [ "aws-credential-types", "aws-runtime", "aws-smithy-async", "aws-smithy-http", - "aws-smithy-json", + "aws-smithy-json 0.61.1", "aws-smithy-runtime", "aws-smithy-runtime-api", "aws-smithy-types", @@ -603,15 +603,15 @@ dependencies = [ [[package]] name = "aws-sdk-sso" -version = "1.48.0" +version = "1.50.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "ded855583fa1d22e88fe39fd6062b062376e50a8211989e07cf5e38d52eb3453" +checksum = "05ca43a4ef210894f93096039ef1d6fa4ad3edfabb3be92b80908b9f2e4b4eab" dependencies = [ "aws-credential-types", "aws-runtime", "aws-smithy-async", "aws-smithy-http", - "aws-smithy-json", + "aws-smithy-json 0.61.1", "aws-smithy-runtime", "aws-smithy-runtime-api", "aws-smithy-types", @@ -625,15 +625,15 @@ dependencies = [ [[package]] name = "aws-sdk-ssooidc" -version = "1.49.0" +version = "1.51.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "9177ea1192e6601ae16c7273385690d88a7ed386a00b74a6bc894d12103cd933" +checksum = "abaf490c2e48eed0bb8e2da2fb08405647bd7f253996e0f93b981958ea0f73b0" dependencies = [ "aws-credential-types", "aws-runtime", "aws-smithy-async", "aws-smithy-http", - "aws-smithy-json", + "aws-smithy-json 0.61.1", "aws-smithy-runtime", "aws-smithy-runtime-api", "aws-smithy-types", @@ -647,15 +647,15 @@ dependencies = [ [[package]] name = "aws-sdk-sts" -version = "1.48.0" +version = "1.51.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "823ef553cf36713c97453e2ddff1eb8f62be7f4523544e2a5db64caf80100f0a" +checksum = "b68fde0d69c8bfdc1060ea7da21df3e39f6014da316783336deff0a9ec28f4bf" dependencies = [ "aws-credential-types", "aws-runtime", "aws-smithy-async", "aws-smithy-http", - "aws-smithy-json", + "aws-smithy-json 0.61.1", "aws-smithy-query", "aws-smithy-runtime", "aws-smithy-runtime-api", @@ -670,9 +670,9 @@ dependencies = [ [[package]] name = "aws-sigv4" -version = "1.2.5" +version = "1.2.6" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "5619742a0d8f253be760bfbb8e8e8368c69e3587e4637af5754e488a611499b1" +checksum = "7d3820e0c08d0737872ff3c7c1f21ebbb6693d832312d6152bf18ef50a5471c2" dependencies = [ "aws-credential-types", "aws-smithy-http", @@ -683,7 +683,7 @@ dependencies = [ "hex", "hmac", "http 0.2.12", - "http 1.1.0", + "http 1.2.0", "once_cell", "percent-encoding", "sha2", @@ -731,6 +731,15 @@ dependencies = [ "aws-smithy-types", ] +[[package]] +name = "aws-smithy-json" +version = "0.61.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ee4e69cc50921eb913c6b662f8d909131bb3e6ad6cb6090d3a39b66fc5c52095" +dependencies = [ + "aws-smithy-types", +] + [[package]] name = "aws-smithy-query" version = "0.60.7" @@ -743,9 +752,9 @@ dependencies = [ [[package]] name = "aws-smithy-runtime" -version = "1.7.3" +version = "1.7.4" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "be28bd063fa91fd871d131fc8b68d7cd4c5fa0869bea68daca50dcb1cbd76be2" +checksum = "9f20685047ca9d6f17b994a07f629c813f08b5bce65523e47124879e60103d45" dependencies = [ "aws-smithy-async", "aws-smithy-http", @@ -770,15 +779,15 @@ dependencies = [ [[package]] name = "aws-smithy-runtime-api" -version = "1.7.2" +version = "1.7.3" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e086682a53d3aa241192aa110fa8dfce98f2f5ac2ead0de84d41582c7e8fdb96" +checksum = "92165296a47a812b267b4f41032ff8069ab7ff783696d217f0994a0d7ab585cd" dependencies = [ "aws-smithy-async", "aws-smithy-types", "bytes", "http 0.2.12", - "http 1.1.0", + "http 1.2.0", "pin-project-lite", "tokio", "tracing", @@ -787,16 +796,16 @@ dependencies = [ [[package]] name = "aws-smithy-types" -version = "1.2.8" +version = "1.2.9" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "07c9cdc179e6afbf5d391ab08c85eac817b51c87e1892a5edb5f7bbdc64314b4" +checksum = "4fbd94a32b3a7d55d3806fe27d98d3ad393050439dd05eb53ece36ec5e3d3510" dependencies = [ "base64-simd", "bytes", "bytes-utils", "futures-core", "http 0.2.12", - "http 1.1.0", + "http 1.2.0", "http-body 0.4.6", "http-body 1.0.1", "http-body-util", @@ -915,9 +924,9 @@ dependencies = [ [[package]] name = "blake3" -version = "1.5.4" +version = "1.5.5" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "d82033247fd8e890df8f740e407ad4d038debb9eb1f40533fffb32e7d17dc6f7" +checksum = "b8ee0c1824c4dea5b5f81736aff91bae041d2c07ee1192bec91054e10e3e601e" dependencies = [ "arrayref", "arrayvec", @@ -989,9 +998,9 @@ checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b" [[package]] name = "bytes" -version = "1.8.0" +version = "1.9.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "9ac0150caa2ae65ca5bd83f25c7de183dea78d4d366469f148435e2acfbad0da" +checksum = "325918d6fe32f23b19878fe4b34794ae41fc19ddbe53b10571a4874d44ffd39b" [[package]] name = "bytes-utils" @@ -1026,9 +1035,9 @@ dependencies = [ [[package]] name = "cc" -version = "1.1.34" +version = "1.2.2" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "67b9470d453346108f93a59222a9a1a5724db32d0a4727b7ab7ace4b4d822dc9" +checksum = "f34d93e62b03caf570cccc334cbc6c2fceca82f39211051345108adcba3eebdc" dependencies = [ "jobserver", "libc", @@ -1091,9 +1100,9 @@ dependencies = [ [[package]] name = "comfy-table" -version = "7.1.1" +version = "7.1.3" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "b34115915337defe99b2aff5c2ce6771e5fbc4079f4b506301f5cf394c8452f7" +checksum = "24f165e7b643266ea80cb858aed492ad9280e3e05ce24d4a99d7d7b889b6a4d9" dependencies = [ "strum", "strum_macros", @@ -1145,6 +1154,16 @@ dependencies = [ "libc", ] +[[package]] +name = "core-foundation" +version = "0.10.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b55271e5c8c478ad3f38ad24ef34923091e0548492a266d19b3c0b4d82574c63" +dependencies = [ + "core-foundation-sys", + "libc", +] + [[package]] name = "core-foundation-sys" version = "0.8.7" @@ -1153,9 +1172,9 @@ checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b" [[package]] name = "cpufeatures" -version = "0.2.14" +version = "0.2.16" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "608697df725056feaccfa42cffdaeeec3fccc4ffc38358ecd19b243e716a78e0" +checksum = "16b80225097f2e5ae4e7179dd2266824648f3e2f49d9134d584b76389d31c4c3" dependencies = [ "libc", ] @@ -1245,9 +1264,9 @@ dependencies = [ [[package]] name = "csv" -version = "1.3.0" +version = "1.3.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "ac574ff4d437a7b5ad237ef331c17ccca63c46479e5b5453eb8e10bb99a759fe" +checksum = "acdc4883a9c96732e4733212c01447ebd805833b7275a73ca3ee080fd77afdaf" dependencies = [ "csv-core", "itoa", @@ -1768,7 +1787,7 @@ checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -1816,12 +1835,12 @@ checksum = "5443807d6dff69373d433ab9ef5378ad8df50ca6298caf15de6e52e24aaf54d5" [[package]] name = "errno" -version = "0.3.9" +version = "0.3.10" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "534c5cf6194dfab3db3242765c03bbe257cf92f22b38f6bc0c58d59108a820ba" +checksum = "33d852cb9b869c2a9b3df2f71a3074817f01e1844f839a144f5fcef059a4eb5d" dependencies = [ "libc", - "windows-sys 0.52.0", + "windows-sys 0.59.0", ] [[package]] @@ -1854,9 +1873,9 @@ dependencies = [ [[package]] name = "event-listener-strategy" -version = "0.5.2" +version = "0.5.3" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "0f214dc438f977e6d4e3500aaa277f5ad94ca83fbbd9b1a15713ce2344ccc5a1" +checksum = "3c3e4e0dd3673c1139bf041f3008816d9cf2946bbfac2945c09e523b8d7b05b2" dependencies = [ "event-listener 5.3.1", "pin-project-lite", @@ -1870,9 +1889,9 @@ checksum = "9afc2bd4d5a73106dd53d10d73d3401c2f32730ba2c0b93ddb888a8983680471" [[package]] name = "fastrand" -version = "2.1.1" +version = "2.2.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e8c02a5121d4ea3eb16a80748c74f5549a5665e4c21333c6098f283870fbdea6" +checksum = "486f806e73c5707928240ddc295403b1b93c96a02038563881c4a2fd84b81ac4" [[package]] name = "filetime" @@ -1904,9 +1923,9 @@ dependencies = [ [[package]] name = "flate2" -version = "1.0.34" +version = "1.0.35" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a1b589b4dc103969ad3cf85c950899926ec64300a1a46d76c03a6072957036f0" +checksum = "c936bfdafb507ebbf50b8074c54fa31c5be9a1e7e5f467dd659697041407d07c" dependencies = [ "crc32fast", "miniz_oxide", @@ -1945,7 +1964,7 @@ dependencies = [ [[package]] name = "fsst" -version = "0.20.0" +version = "0.20.1" dependencies = [ "rand", ] @@ -2006,9 +2025,9 @@ checksum = "9e5c1b78ca4aae1ac06c48a526a655760685149f0d465d21f37abfe57ce075c6" [[package]] name = "futures-lite" -version = "2.4.0" +version = "2.5.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "3f1fa2f9765705486b33fd2acf1577f8ec449c2ba1f318ae5447697b7c08d210" +checksum = "cef40d21ae2c515b51041df9ed313ed21e572df340ea58a922a0aefe7e8891a1" dependencies = [ "fastrand", "futures-core", @@ -2025,7 +2044,7 @@ checksum = "162ee34ebcb7c64a8abebc059ce0fee27c2262618d7b60ed8faf72fef13c3650" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -2126,16 +2145,16 @@ dependencies = [ [[package]] name = "h2" -version = "0.4.6" +version = "0.4.7" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "524e8ac6999421f49a846c2d4411f337e53497d8ec55d67753beffa43c5d9205" +checksum = "ccae279728d634d083c00f6099cb58f01cc99c145b84b8be2f6c74618d79922e" dependencies = [ "atomic-waker", "bytes", "fnv", "futures-core", "futures-sink", - "http 1.1.0", + "http 1.2.0", "indexmap", "slab", "tokio", @@ -2166,9 +2185,9 @@ dependencies = [ [[package]] name = "hashbrown" -version = "0.15.1" +version = "0.15.2" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "3a9bfc1af68b1726ea47d3d5109de126281def866b33970e10fbab11b5dafab3" +checksum = "bf151400ff0baff5465007dd2f3e717f3fe502074ca563069ce3a6629d07b289" dependencies = [ "allocator-api2", "equivalent", @@ -2253,9 +2272,9 @@ dependencies = [ [[package]] name = "http" -version = "1.1.0" +version = "1.2.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "21b9ddb458710bc376481b842f5da65cdf31522de232c1ca8146abce2a358258" +checksum = "f16ca2af56261c99fba8bac40a10251ce8188205a4c448fbb745a2e4daa76fea" dependencies = [ "bytes", "fnv", @@ -2280,7 +2299,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "1efedce1fb8e6913f23e0c92de8e62cd5b772a67e7b3946df930a62566c93184" dependencies = [ "bytes", - "http 1.1.0", + "http 1.2.0", ] [[package]] @@ -2291,7 +2310,7 @@ checksum = "793429d76616a256bcb62c2a2ec2bed781c8307e797e2598c50010f2bee2544f" dependencies = [ "bytes", "futures-util", - "http 1.1.0", + "http 1.2.0", "http-body 1.0.1", "pin-project-lite", ] @@ -2340,15 +2359,15 @@ dependencies = [ [[package]] name = "hyper" -version = "1.5.0" +version = "1.5.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "bbbff0a806a4728c99295b254c8838933b5b082d75e3cb70c8dab21fdfbcfa9a" +checksum = "97818827ef4f364230e16705d4706e2897df2bb60617d6ca15d598025a3c481f" dependencies = [ "bytes", "futures-channel", "futures-util", - "h2 0.4.6", - "http 1.1.0", + "h2 0.4.7", + "http 1.2.0", "http-body 1.0.1", "httparse", "itoa", @@ -2381,11 +2400,11 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "08afdbb5c31130e3034af566421053ab03787c640246a446327f550d11bcb333" dependencies = [ "futures-util", - "http 1.1.0", - "hyper 1.5.0", + "http 1.2.0", + "hyper 1.5.1", "hyper-util", - "rustls 0.23.16", - "rustls-native-certs 0.8.0", + "rustls 0.23.19", + "rustls-native-certs 0.8.1", "rustls-pki-types", "tokio", "tokio-rustls 0.26.0", @@ -2401,9 +2420,9 @@ dependencies = [ "bytes", "futures-channel", "futures-util", - "http 1.1.0", + "http 1.2.0", "http-body 1.0.1", - "hyper 1.5.0", + "hyper 1.5.1", "pin-project-lite", "socket2", "tokio", @@ -2558,7 +2577,7 @@ checksum = "1ec89e9337638ecdc08744df490b221a7399bf8d164eb52a665454e60e075ad6" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -2584,12 +2603,12 @@ dependencies = [ [[package]] name = "indexmap" -version = "2.6.0" +version = "2.7.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "707907fe3c25f5424cce2cb7e1cbcafee6bdbe735ca90ef77c29e84591e5b9da" +checksum = "62f822373a4fe84d4bb149bf54e584a7f4abec90e072ed49cda0edea5b95471f" dependencies = [ "equivalent", - "hashbrown 0.15.1", + "hashbrown 0.15.2", ] [[package]] @@ -2677,9 +2696,9 @@ dependencies = [ [[package]] name = "itoa" -version = "1.0.11" +version = "1.0.14" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "49f1f14873335454500d59611f1cf4a4b0f786f9ac11f4312a78e4cf2566695b" +checksum = "d75a2a4b1b190afb6f5425f10f6a8f959d2ea0b9c2b1d79553551850539e4674" [[package]] name = "jobserver" @@ -2692,10 +2711,11 @@ dependencies = [ [[package]] name = "js-sys" -version = "0.3.72" +version = "0.3.74" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "6a88f1bda2bd75b0452a14784937d796722fdebfe50df998aeb3f0b7603019a9" +checksum = "a865e038f7f6ed956f788f0d7d60c541fff74c7bd74272c5d4cf15c63743e705" dependencies = [ + "once_cell", "wasm-bindgen", ] @@ -2710,7 +2730,7 @@ dependencies = [ [[package]] name = "lance" -version = "0.20.0" +version = "0.20.1" dependencies = [ "arrow", "arrow-arith", @@ -2772,7 +2792,7 @@ dependencies = [ [[package]] name = "lance-arrow" -version = "0.20.0" +version = "0.20.1" dependencies = [ "arrow-array", "arrow-buffer", @@ -2789,7 +2809,7 @@ dependencies = [ [[package]] name = "lance-core" -version = "0.20.0" +version = "0.20.1" dependencies = [ "arrow-array", "arrow-buffer", @@ -2825,7 +2845,7 @@ dependencies = [ [[package]] name = "lance-datafusion" -version = "0.20.0" +version = "0.20.1" dependencies = [ "arrow", "arrow-array", @@ -2851,7 +2871,7 @@ dependencies = [ [[package]] name = "lance-datagen" -version = "0.20.0" +version = "0.20.1" dependencies = [ "arrow", "arrow-array", @@ -2866,7 +2886,7 @@ dependencies = [ [[package]] name = "lance-encoding" -version = "0.20.0" +version = "0.20.1" dependencies = [ "arrayref", "arrow", @@ -2904,7 +2924,7 @@ dependencies = [ [[package]] name = "lance-file" -version = "0.20.0" +version = "0.20.1" dependencies = [ "arrow-arith", "arrow-array", @@ -2938,7 +2958,7 @@ dependencies = [ [[package]] name = "lance-index" -version = "0.20.0" +version = "0.20.1" dependencies = [ "arrow", "arrow-array", @@ -2989,7 +3009,7 @@ dependencies = [ [[package]] name = "lance-io" -version = "0.20.0" +version = "0.20.1" dependencies = [ "arrow", "arrow-arith", @@ -3028,7 +3048,7 @@ dependencies = [ [[package]] name = "lance-linalg" -version = "0.20.0" +version = "0.20.1" dependencies = [ "arrow-array", "arrow-ord", @@ -3051,7 +3071,7 @@ dependencies = [ [[package]] name = "lance-table" -version = "0.20.0" +version = "0.20.1" dependencies = [ "arrow", "arrow-array", @@ -3166,9 +3186,9 @@ dependencies = [ [[package]] name = "libc" -version = "0.2.161" +version = "0.2.167" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "8e9489c2807c139ffd9c1794f4af0ebe86a828db53ecdc7fea2111d0fed085d1" +checksum = "09d6582e104315a817dff97f75133544b2e094ee22447d2acf4a74e189ba06fc" [[package]] name = "libm" @@ -3195,9 +3215,9 @@ checksum = "78b3ae25bc7c8c38cec158d1f2757ee79e9b3740fbc7ccf0e59e4b08d793fa89" [[package]] name = "litemap" -version = "0.7.3" +version = "0.7.4" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "643cb0b8d4fcc284004d5fd0d67ccf61dfffadb7f75e1e71bc420f4688a3a704" +checksum = "4ee93343901ab17bd981295f2cf0026d4ad018c7c31ba84549a4ddbb47a45104" [[package]] name = "lock_api" @@ -3224,7 +3244,7 @@ version = "0.12.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "234cf4f4a04dc1f57e24b96cc0cd600cf2af460d4161ac5ecdd0af8e1f3b2a38" dependencies = [ - "hashbrown 0.15.1", + "hashbrown 0.15.2", ] [[package]] @@ -3320,11 +3340,10 @@ dependencies = [ [[package]] name = "mio" -version = "1.0.2" +version = "1.0.3" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "80e04d1dcff3aae0704555fe5fee3bcfaf3d1fdf8a7e521d5b9d2b42acb52cec" +checksum = "2886843bf800fba2e3377cff24abf6379b4c4d5c6681eaf9ea5b0d15090450bd" dependencies = [ - "hermit-abi 0.3.9", "libc", "wasi", "windows-sys 0.52.0", @@ -3358,7 +3377,7 @@ dependencies = [ "rustc_version", "smallvec", "tagptr", - "thiserror", + "thiserror 1.0.69", "triomphe", "uuid", ] @@ -3521,7 +3540,7 @@ dependencies = [ "chrono", "futures", "humantime", - "hyper 1.5.0", + "hyper 1.5.1", "itertools 0.13.0", "md-5", "parking_lot", @@ -3665,7 +3684,7 @@ dependencies = [ "flate2", "futures", "half", - "hashbrown 0.15.1", + "hashbrown 0.15.2", "lz4_flex", "num", "num-bigint", @@ -3821,7 +3840,7 @@ checksum = "3c0f5fad0874fc7abcd4d750e76917eaebbecaa2c20bde22e1dbeeba8beb758c" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -3855,9 +3874,9 @@ checksum = "953ec861398dccce10c670dfeaf3ec4911ca479e9c02154b3a215178c5f566f2" [[package]] name = "polling" -version = "3.7.3" +version = "3.7.4" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "cc2790cd301dec6cd3b7a025e4815cf825724a51c98dccfe6a3e55f05ffb6511" +checksum = "a604568c3202727d1507653cb121dbd627a58684eb09a820fd746bee38b4442f" dependencies = [ "cfg-if", "concurrent-queue", @@ -3870,9 +3889,9 @@ dependencies = [ [[package]] name = "portable-atomic" -version = "1.9.0" +version = "1.10.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "cc9c68a3f6da06753e9335d63e27f6b9754dd1920d941135b7ea8224f141adb2" +checksum = "280dc24453071f1b63954171985a0b0d30058d287960968b9b2aca264c8d4ee6" [[package]] name = "powerfmt" @@ -3906,14 +3925,14 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "64d1ec885c64d0457d564db4ec299b2dae3f9c02808b8ad9c3a089c591b18033" dependencies = [ "proc-macro2", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] name = "proc-macro2" -version = "1.0.89" +version = "1.0.92" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "f139b0662de085916d1fb67d2b4169d1addddda1919e696f3252b740b629986e" +checksum = "37d3544b3f2748c54e147655edb5025752e2303145b5aefb3c3ea2c78b973bb0" dependencies = [ "unicode-ident", ] @@ -3987,7 +4006,7 @@ dependencies = [ "prost 0.12.6", "prost-types 0.12.6", "regex", - "syn 2.0.87", + "syn 2.0.90", "tempfile", ] @@ -4008,7 +4027,7 @@ dependencies = [ "prost 0.13.3", "prost-types 0.13.3", "regex", - "syn 2.0.87", + "syn 2.0.90", "tempfile", ] @@ -4035,7 +4054,7 @@ dependencies = [ "itertools 0.12.1", "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -4048,7 +4067,7 @@ dependencies = [ "itertools 0.13.0", "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -4080,7 +4099,7 @@ dependencies = [ [[package]] name = "pylance" -version = "0.20.0" +version = "0.20.1" dependencies = [ "arrow", "arrow-array", @@ -4168,7 +4187,7 @@ dependencies = [ "proc-macro2", "pyo3-macros-backend", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -4181,7 +4200,7 @@ dependencies = [ "proc-macro2", "pyo3-build-config", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -4211,44 +4230,47 @@ dependencies = [ [[package]] name = "quinn" -version = "0.11.5" +version = "0.11.6" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "8c7c5fdde3cdae7203427dc4f0a68fe0ed09833edc525a03456b153b79828684" +checksum = "62e96808277ec6f97351a2380e6c25114bc9e67037775464979f3037c92d05ef" dependencies = [ "bytes", "pin-project-lite", "quinn-proto", "quinn-udp", - "rustc-hash 2.0.0", - "rustls 0.23.16", + "rustc-hash 2.1.0", + "rustls 0.23.19", "socket2", - "thiserror", + "thiserror 2.0.4", "tokio", "tracing", ] [[package]] name = "quinn-proto" -version = "0.11.8" +version = "0.11.9" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "fadfaed2cd7f389d0161bb73eeb07b7b78f8691047a6f3e73caaeae55310a4a6" +checksum = "a2fe5ef3495d7d2e377ff17b1a8ce2ee2ec2a18cde8b6ad6619d65d0701c135d" dependencies = [ "bytes", + "getrandom", "rand", "ring", - "rustc-hash 2.0.0", - "rustls 0.23.16", + "rustc-hash 2.1.0", + "rustls 0.23.19", + "rustls-pki-types", "slab", - "thiserror", + "thiserror 2.0.4", "tinyvec", "tracing", + "web-time", ] [[package]] name = "quinn-udp" -version = "0.5.6" +version = "0.5.7" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e346e016eacfff12233c243718197ca12f148c84e1e84268a896699b41c71780" +checksum = "7d5a626c6807713b15cac82a6acaccd6043c9a5408c24baae07611fec3f243da" dependencies = [ "cfg_aliases", "libc", @@ -4374,7 +4396,7 @@ checksum = "ba009ff324d1fc1b900bd1fdb31564febe58a8ccc8a6fdbb93b543d33b13ca43" dependencies = [ "getrandom", "libredox", - "thiserror", + "thiserror 1.0.69", ] [[package]] @@ -4391,9 +4413,9 @@ dependencies = [ [[package]] name = "regex-automata" -version = "0.4.8" +version = "0.4.9" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "368758f23274712b504848e9d5a6f010445cc8b87a7cdb4d7cbee666c1288da3" +checksum = "809e8dc61f6de73b46c85f4c96486310fe304c434cfa43669d7b40f711150908" dependencies = [ "aho-corasick", "memchr", @@ -4432,11 +4454,11 @@ dependencies = [ "bytes", "futures-core", "futures-util", - "h2 0.4.6", - "http 1.1.0", + "h2 0.4.7", + "http 1.2.0", "http-body 1.0.1", "http-body-util", - "hyper 1.5.0", + "hyper 1.5.1", "hyper-rustls 0.27.3", "hyper-util", "ipnet", @@ -4447,8 +4469,8 @@ dependencies = [ "percent-encoding", "pin-project-lite", "quinn", - "rustls 0.23.16", - "rustls-native-certs 0.8.0", + "rustls 0.23.19", + "rustls-native-certs 0.8.1", "rustls-pemfile 2.2.0", "rustls-pki-types", "serde", @@ -4484,9 +4506,9 @@ dependencies = [ [[package]] name = "roaring" -version = "0.10.6" +version = "0.10.7" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "8f4b84ba6e838ceb47b41de5194a60244fac43d9fe03b71dbe8c5a201081d6d1" +checksum = "f81dc953b2244ddd5e7860cb0bb2a790494b898ef321d4aff8e260efab60cc88" dependencies = [ "bytemuck", "byteorder", @@ -4516,9 +4538,9 @@ checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2" [[package]] name = "rustc-hash" -version = "2.0.0" +version = "2.1.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "583034fd73374156e66797ed8e5b0d5690409c9226b22d87cb7f19821c05d152" +checksum = "c7fb8039b3032c191086b10f11f319a6e99e1e82889c5cc6046f515c9db1d497" [[package]] name = "rustc_version" @@ -4531,9 +4553,9 @@ dependencies = [ [[package]] name = "rustix" -version = "0.38.39" +version = "0.38.41" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "375116bee2be9ed569afe2154ea6a99dfdffd257f533f187498c2a8f5feaf4ee" +checksum = "d7f649912bc1495e167a6edee79151c84b1bad49748cb4f1f1167f459f6224f6" dependencies = [ "bitflags 2.6.0", "errno", @@ -4556,9 +4578,9 @@ dependencies = [ [[package]] name = "rustls" -version = "0.23.16" +version = "0.23.19" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "eee87ff5d9b36712a58574e12e9f0ea80f915a5b0ac518d322b24a465617925e" +checksum = "934b404430bb06b3fae2cba809eb45a1ab1aecd64491213d7c3301b88393f8d1" dependencies = [ "log", "once_cell", @@ -4578,20 +4600,19 @@ dependencies = [ "openssl-probe", "rustls-pemfile 1.0.4", "schannel", - "security-framework", + "security-framework 2.11.1", ] [[package]] name = "rustls-native-certs" -version = "0.8.0" +version = "0.8.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "fcaf18a4f2be7326cd874a5fa579fae794320a0f388d365dca7e480e55f83f8a" +checksum = "7fcff2dd52b58a8d98a70243663a0d234c4e2b79235637849d15913394a247d3" dependencies = [ "openssl-probe", - "rustls-pemfile 2.2.0", "rustls-pki-types", "schannel", - "security-framework", + "security-framework 3.0.1", ] [[package]] @@ -4617,6 +4638,9 @@ name = "rustls-pki-types" version = "1.10.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "16f1201b3c9a7ee8039bcadc17b7e605e2945b27eee7631788c1bd2b0643674b" +dependencies = [ + "web-time", +] [[package]] name = "rustls-webpki" @@ -4662,9 +4686,9 @@ dependencies = [ [[package]] name = "schannel" -version = "0.1.26" +version = "0.1.27" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "01227be5826fa0690321a2ba6c5cd57a19cf3f6a09e76973b58e61de6ab9d1c1" +checksum = "1f29ebaa345f945cec9fbbc532eb307f0fdad8161f281b6369539c8d84876b3d" dependencies = [ "windows-sys 0.59.0", ] @@ -4690,7 +4714,7 @@ dependencies = [ "proc-macro2", "quote", "serde_derive_internals", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -4716,7 +4740,20 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "897b2245f0b511c87893af39b033e5ca9cce68824c4d7e7630b5a1d339658d02" dependencies = [ "bitflags 2.6.0", - "core-foundation", + "core-foundation 0.9.4", + "core-foundation-sys", + "libc", + "security-framework-sys", +] + +[[package]] +name = "security-framework" +version = "3.0.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e1415a607e92bec364ea2cf9264646dcce0f91e6d65281bd6f2819cca3bf39c8" +dependencies = [ + "bitflags 2.6.0", + "core-foundation 0.10.0", "core-foundation-sys", "libc", "security-framework-sys", @@ -4724,9 +4761,9 @@ dependencies = [ [[package]] name = "security-framework-sys" -version = "2.12.0" +version = "2.12.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "ea4a292869320c0272d7bc55a5a6aafaff59b4f63404a003887b679a2e05b4b6" +checksum = "fa39c7303dc58b5543c94d22c1766b0d31f2ee58306363ea622b10bbc075eaa2" dependencies = [ "core-foundation-sys", "libc", @@ -4749,22 +4786,22 @@ checksum = "a3f0bf26fd526d2a95683cd0f87bf103b8539e2ca1ef48ce002d67aad59aa0b4" [[package]] name = "serde" -version = "1.0.214" +version = "1.0.215" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "f55c3193aca71c12ad7890f1785d2b73e1b9f63a0bbc353c08ef26fe03fc56b5" +checksum = "6513c1ad0b11a9376da888e3e0baa0077f1aed55c17f50e7b2397136129fb88f" dependencies = [ "serde_derive", ] [[package]] name = "serde_derive" -version = "1.0.214" +version = "1.0.215" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "de523f781f095e28fa605cdce0f8307e451cc0fd14e2eb4cd2e98a355b147766" +checksum = "ad1e866f866923f252f05c889987993144fb74e722403468a4ebd70c3cd756c0" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -4775,14 +4812,14 @@ checksum = "18d26a20a969b9e3fdf2fc2d9f21eda6c40e2de84c9408bb5d3b05d499aae711" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] name = "serde_json" -version = "1.0.132" +version = "1.0.133" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "d726bfaff4b320266d395898905d0eba0345aae23b54aee3a737e260fd46db03" +checksum = "c7fceb2473b9166b2294ef05efcb65a3db80803f0b03ef86a5fc88a2b85ee377" dependencies = [ "itoa", "memchr", @@ -4799,7 +4836,7 @@ dependencies = [ "proc-macro2", "quote", "serde", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -4941,7 +4978,7 @@ dependencies = [ "heck 0.5.0", "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -4952,9 +4989,9 @@ checksum = "1b6b67fb9a61334225b5b790716f609cd58395f895b3fe8b328786812a40bc3b" [[package]] name = "socket2" -version = "0.5.7" +version = "0.5.8" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "ce305eb0b4296696835b71df73eb912e0f1ffd2556a501fcede6e0c50349191c" +checksum = "c970269d99b64e60ec3bd6ad27270092a5394c4e309314b18ae3fe575695fbe8" dependencies = [ "libc", "windows-sys 0.52.0", @@ -4984,7 +5021,7 @@ checksum = "01b2e185515564f15375f593fb966b5718bc624ba77fe49fa4616ad619690554" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -5030,7 +5067,7 @@ dependencies = [ "proc-macro2", "quote", "rustversion", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -5052,7 +5089,7 @@ dependencies = [ "serde", "serde_json", "serde_yaml", - "syn 2.0.87", + "syn 2.0.90", "typify", "walkdir", ] @@ -5076,9 +5113,9 @@ dependencies = [ [[package]] name = "syn" -version = "2.0.87" +version = "2.0.90" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "25aa4ce346d03a6dcd68dd8b4010bcb74e54e62c90c573f394c46eae99aba32d" +checksum = "919d3b74a5dd0ccd15aeb8f93e7006bd9e14c295087c9896a110f490752bcf31" dependencies = [ "proc-macro2", "quote", @@ -5087,9 +5124,9 @@ dependencies = [ [[package]] name = "sync_wrapper" -version = "1.0.1" +version = "1.0.2" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a7065abeca94b6a8a577f9bd45aa0867a2238b74e8eb67cf10d492bc39351394" +checksum = "0bf256ce5efdfa370213c1dabab5935a12e49f2c58d15e9eac2870d3b4f27263" dependencies = [ "futures-core", ] @@ -5102,7 +5139,7 @@ checksum = "c8af7666ab7b6390ab78131fb5b0fce11d6b7a6951602017c35fa82800708971" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -5156,7 +5193,7 @@ dependencies = [ "tantivy-stacker", "tantivy-tokenizer-api", "tempfile", - "thiserror", + "thiserror 1.0.69", "time", "uuid", "winapi", @@ -5277,9 +5314,9 @@ checksum = "61c41af27dd6d1e27b1b16b489db798443478cef1f06a660c96db617ba5de3b1" [[package]] name = "tempfile" -version = "3.13.0" +version = "3.14.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "f0f2c9fc62d0beef6951ccffd757e241266a2c833136efbe35af6cd2567dca5b" +checksum = "28cce251fcbc87fac86a866eeb0d6c2d536fc16d06f184bb61aeae11aa4cee0c" dependencies = [ "cfg-if", "fastrand", @@ -5322,28 +5359,48 @@ dependencies = [ "prost 0.12.6", "prost-build 0.12.6", "tar", - "thiserror", + "thiserror 1.0.69", "ureq", ] [[package]] name = "thiserror" -version = "1.0.68" +version = "1.0.69" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b6aaf5339b578ea85b50e080feb250a3e8ae8cfcdff9a461c9ec2904bc923f52" +dependencies = [ + "thiserror-impl 1.0.69", +] + +[[package]] +name = "thiserror" +version = "2.0.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2f49a1853cf82743e3b7950f77e0f4d622ca36cf4317cba00c767838bac8d490" +dependencies = [ + "thiserror-impl 2.0.4", +] + +[[package]] +name = "thiserror-impl" +version = "1.0.69" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "02dd99dc800bbb97186339685293e1cc5d9df1f8fae2d0aecd9ff1c77efea892" +checksum = "4fee6c4efc90059e10f81e6d42c60a18f76588c3d74cb83a0b242a2b6c7504c1" dependencies = [ - "thiserror-impl", + "proc-macro2", + "quote", + "syn 2.0.90", ] [[package]] name = "thiserror-impl" -version = "1.0.68" +version = "2.0.4" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a7c61ec9a6f64d2793d8a45faba21efbe3ced62a886d44c36a009b2b519b4c7e" +checksum = "8381894bb3efe0c4acac3ded651301ceee58a15d47c2e34885ed1908ad667061" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -5369,9 +5426,9 @@ dependencies = [ [[package]] name = "time" -version = "0.3.36" +version = "0.3.37" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "5dfd88e563464686c916c7e46e623e520ddc6d79fa6641390f2e3fa86e83e885" +checksum = "35e7868883861bd0e56d9ac6efcaaca0d6d5d82a2a7ec8209ff492c07cf37b21" dependencies = [ "deranged", "itoa", @@ -5390,9 +5447,9 @@ checksum = "ef927ca75afb808a4d64dd374f00a2adf8d0fcff8e7b184af886c3c87ec4a3f3" [[package]] name = "time-macros" -version = "0.2.18" +version = "0.2.19" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "3f252a68540fde3a3877aeea552b832b40ab9a69e318efd078774a01ddee1ccf" +checksum = "2834e6017e3e5e4b9834939793b282bc03b37a3336245fa820e35e233e2a85de" dependencies = [ "num-conv", "time-core", @@ -5434,9 +5491,9 @@ checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20" [[package]] name = "tokio" -version = "1.41.0" +version = "1.42.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "145f3413504347a2be84393cc8a7d2fb4d863b375909ea59f2158261aa258bbb" +checksum = "5cec9b21b0450273377fc97bd4c33a8acffc8c996c987a7c5b319a0083707551" dependencies = [ "backtrace", "bytes", @@ -5457,7 +5514,7 @@ checksum = "693d596312e88961bc67d7f1f97af8a70227d9f90c31bba5806eec004978d752" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -5476,7 +5533,7 @@ version = "0.26.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "0c7bc40d0e5a97695bb96e27995cd3a08538541b0a846f65bba7a359f36700d4" dependencies = [ - "rustls 0.23.16", + "rustls 0.23.19", "rustls-pki-types", "tokio", ] @@ -5494,9 +5551,9 @@ dependencies = [ [[package]] name = "tokio-util" -version = "0.7.12" +version = "0.7.13" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "61e7c3654c13bcd040d4a03abee2c75b1d14a37b423cf5a813ceae1cc903ec6a" +checksum = "d7fcaa8d55a2bdd6b83ace262b016eca0d79ee02818c5c1bcdf0305114081078" dependencies = [ "bytes", "futures-core", @@ -5513,9 +5570,9 @@ checksum = "8df9b6e13f2d32c91b9bd719c00d1958837bc7dec474d94952798cc8e69eeec3" [[package]] name = "tracing" -version = "0.1.40" +version = "0.1.41" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "c3523ab5a71916ccf420eebdf5521fcef02141234bbc0b8a49f2fdc4544364ef" +checksum = "784e0ac535deb450455cbfa28a6f0df145ea1bb7ae51b821cf5e7927fdcfbdd0" dependencies = [ "pin-project-lite", "tracing-attributes", @@ -5524,13 +5581,13 @@ dependencies = [ [[package]] name = "tracing-attributes" -version = "0.1.27" +version = "0.1.28" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "34704c8d6ebcbc939824180af020566b01a7c01f80641264eba0999f6c2b6be7" +checksum = "395ae124c09f9e6918a2310af6038fba074bcf474ac352496d5910dd59a2226d" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -5546,9 +5603,9 @@ dependencies = [ [[package]] name = "tracing-core" -version = "0.1.32" +version = "0.1.33" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "c06d3da6113f116aaee68e4d601191614c9053067f9ab7f6edbcb161237daa54" +checksum = "e672c95779cf947c5311f83787af4fa8fffd12fb27e4993211a84bdfd9610f9c" dependencies = [ "once_cell", "valuable", @@ -5567,9 +5624,9 @@ dependencies = [ [[package]] name = "tracing-subscriber" -version = "0.3.18" +version = "0.3.19" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "ad0f048c97dbd9faa9b7df56362b8ebcaa52adb06b498c050d2f4e32f90a7a8b" +checksum = "e8189decb5ac0fa7bc8b96b7cb9b2701d60d48805aca84a238004d665fcc4008" dependencies = [ "nu-ansi-term", "sharded-slab", @@ -5632,8 +5689,8 @@ dependencies = [ "semver", "serde", "serde_json", - "syn 2.0.87", - "thiserror", + "syn 2.0.90", + "thiserror 1.0.69", "unicode-ident", ] @@ -5650,15 +5707,15 @@ dependencies = [ "serde", "serde_json", "serde_tokenstream", - "syn 2.0.87", + "syn 2.0.90", "typify-impl", ] [[package]] name = "unicode-ident" -version = "1.0.13" +version = "1.0.14" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e91b56cd4cadaeb79bbf1a5645f6b4f8dc5bde8834ad5894a8db35fda9efa1fe" +checksum = "adb9e6ca4f869e1180728b7950e35922a7fc6397f7b641499e8f3ef06e50dc83" [[package]] name = "unicode-segmentation" @@ -5668,9 +5725,9 @@ checksum = "f6ccf251212114b54433ec949fd6a7841275f9ada20dddd2f29e9ceea4501493" [[package]] name = "unicode-width" -version = "0.1.14" +version = "0.2.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "7dd6e30e90baa6f72411720665d41d89b9a3d039dc45b8faea1ddd07f617f6af" +checksum = "1fc81956842c57dac11422a97c3b8195a1ff727f06e85c84ed2e8aa277c9a0fd" [[package]] name = "unindent" @@ -5692,15 +5749,15 @@ checksum = "8ecb6da28b8a351d773b68d5825ac39017e680750f980f3a1a85cd8dd28a47c1" [[package]] name = "ureq" -version = "2.10.1" +version = "2.12.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "b74fc6b57825be3373f7054754755f03ac3a8f5d70015ccad699ba2029956f4a" +checksum = "02d1a66277ed75f640d608235660df48c8e3c19f3b4edb6a263315626cc3c01d" dependencies = [ "base64 0.22.1", "flate2", "log", "once_cell", - "rustls 0.23.16", + "rustls 0.23.19", "rustls-pki-types", "url", "webpki-roots", @@ -5708,9 +5765,9 @@ dependencies = [ [[package]] name = "url" -version = "2.5.3" +version = "2.5.4" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "8d157f1b96d14500ffdc1f10ba712e780825526c03d9a49b4d0324b0d9113ada" +checksum = "32f8b686cadd1473f4bd0117a5d28d36b1ade384ea9b5069a1c40aefed7fda60" dependencies = [ "form_urlencoded", "idna", @@ -5802,9 +5859,9 @@ checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423" [[package]] name = "wasm-bindgen" -version = "0.2.95" +version = "0.2.97" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "128d1e363af62632b8eb57219c8fd7877144af57558fb2ef0368d0087bddeb2e" +checksum = "d15e63b4482863c109d70a7b8706c1e364eb6ea449b201a76c5b89cedcec2d5c" dependencies = [ "cfg-if", "once_cell", @@ -5813,36 +5870,37 @@ dependencies = [ [[package]] name = "wasm-bindgen-backend" -version = "0.2.95" +version = "0.2.97" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "cb6dd4d3ca0ddffd1dd1c9c04f94b868c37ff5fac97c30b97cff2d74fce3a358" +checksum = "8d36ef12e3aaca16ddd3f67922bc63e48e953f126de60bd33ccc0101ef9998cd" dependencies = [ "bumpalo", "log", "once_cell", "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", "wasm-bindgen-shared", ] [[package]] name = "wasm-bindgen-futures" -version = "0.4.45" +version = "0.4.47" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "cc7ec4f8827a71586374db3e87abdb5a2bb3a15afed140221307c3ec06b1f63b" +checksum = "9dfaf8f50e5f293737ee323940c7d8b08a66a95a419223d9f41610ca08b0833d" dependencies = [ "cfg-if", "js-sys", + "once_cell", "wasm-bindgen", "web-sys", ] [[package]] name = "wasm-bindgen-macro" -version = "0.2.95" +version = "0.2.97" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e79384be7f8f5a9dd5d7167216f022090cf1f9ec128e6e6a482a2cb5c5422c56" +checksum = "705440e08b42d3e4b36de7d66c944be628d579796b8090bfa3471478a2260051" dependencies = [ "quote", "wasm-bindgen-macro-support", @@ -5850,22 +5908,22 @@ dependencies = [ [[package]] name = "wasm-bindgen-macro-support" -version = "0.2.95" +version = "0.2.97" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "26c6ab57572f7a24a4985830b120de1594465e5d500f24afe89e16b4e833ef68" +checksum = "98c9ae5a76e46f4deecd0f0255cc223cfa18dc9b261213b8aa0c7b36f61b3f1d" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", "wasm-bindgen-backend", "wasm-bindgen-shared", ] [[package]] name = "wasm-bindgen-shared" -version = "0.2.95" +version = "0.2.97" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "65fc09f10666a9f147042251e0dda9c18f166ff7de300607007e96bdebc1068d" +checksum = "6ee99da9c5ba11bd675621338ef6fa52296b76b83305e9b6e5c77d4c286d6d49" [[package]] name = "wasm-streams" @@ -5882,9 +5940,19 @@ dependencies = [ [[package]] name = "web-sys" -version = "0.3.72" +version = "0.3.74" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a98bc3c33f0fe7e59ad7cd041b89034fa82a7c2d4365ca538dda6cdaf513863c" +dependencies = [ + "js-sys", + "wasm-bindgen", +] + +[[package]] +name = "web-time" +version = "1.1.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "f6488b90108c040df0fe62fa815cbdee25124641df01814dd7282749234c6112" +checksum = "5a6580f308b1fad9207618087a65c04e7a10bc77e02c8e84e9b00dd4b12fa0bb" dependencies = [ "js-sys", "wasm-bindgen", @@ -5892,9 +5960,9 @@ dependencies = [ [[package]] name = "webpki-roots" -version = "0.26.6" +version = "0.26.7" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "841c67bff177718f1d4dfefde8d8f0e78f9b6589319ba88312f567fc5841a958" +checksum = "5d642ff16b7e79272ae451b7322067cdc17cadf68c23264be9d94a32319efe7e" dependencies = [ "rustls-pki-types", ] @@ -6178,9 +6246,9 @@ dependencies = [ [[package]] name = "yoke" -version = "0.7.4" +version = "0.7.5" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "6c5b1314b079b0930c31e3af543d8ee1757b1951ae1e1565ec704403a7240ca5" +checksum = "120e6aef9aa629e3d4f52dc8cc43a015c7724194c97dfaf45180d2daf2b77f40" dependencies = [ "serde", "stable_deref_trait", @@ -6190,13 +6258,13 @@ dependencies = [ [[package]] name = "yoke-derive" -version = "0.7.4" +version = "0.7.5" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "28cc31741b18cb6f1d5ff12f5b7523e3d6eb0852bbbad19d73905511d9849b95" +checksum = "2380878cad4ac9aac1e2435f3eb4020e8374b5f13c296cb75b4620ff8e229154" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", "synstructure", ] @@ -6218,27 +6286,27 @@ checksum = "fa4f8080344d4671fb4e831a13ad1e68092748387dfc4f55e356242fae12ce3e" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] name = "zerofrom" -version = "0.1.4" +version = "0.1.5" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "91ec111ce797d0e0784a1116d0ddcdbea84322cd79e5d5ad173daeba4f93ab55" +checksum = "cff3ee08c995dee1859d998dea82f7374f2826091dd9cd47def953cae446cd2e" dependencies = [ "zerofrom-derive", ] [[package]] name = "zerofrom-derive" -version = "0.1.4" +version = "0.1.5" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "0ea7b4a3637ea8669cedf0f1fd5c286a17f3de97b8dd5a70a6c167a1730e63a5" +checksum = "595eed982f7d355beb85837f651fa22e90b3c044842dc7f2c2842c086f295808" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", "synstructure", ] @@ -6267,7 +6335,7 @@ checksum = "6eafa6dfb17584ea3e2bd6e76e0cc15ad7af12b09abdd1ca55961bed9b1063c6" dependencies = [ "proc-macro2", "quote", - "syn 2.0.87", + "syn 2.0.90", ] [[package]] @@ -6290,9 +6358,9 @@ dependencies = [ [[package]] name = "zstd-sys" -version = "2.0.12+zstd.1.5.6" +version = "2.0.13+zstd.1.5.6" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "0a4e40c320c3cb459d9a9ff6de98cff88f4751ee9275d140e2be94a2b74e4c13" +checksum = "38ff0f21cfee8f97d94cef41359e0c89aa6113028ab0291aa8ca0038995a95aa" dependencies = [ "cc", "pkg-config", diff --git a/rust/lance-index/src/vector/pq.rs b/rust/lance-index/src/vector/pq.rs index 467599157b..7e325c1397 100644 --- a/rust/lance-index/src/vector/pq.rs +++ b/rust/lance-index/src/vector/pq.rs @@ -11,7 +11,7 @@ use arrow_array::{cast::AsArray, Array, FixedSizeListArray, UInt8Array}; use arrow_array::{ArrayRef, Float32Array, PrimitiveArray}; use arrow_schema::DataType; use deepsize::DeepSizeOf; -use distance::{build_distance_table_dot, compute_dot_distance}; +use distance::build_distance_table_dot; use lance_arrow::*; use lance_core::{Error, Result}; use lance_linalg::distance::{DistanceType, Dot, L2}; @@ -28,7 +28,7 @@ pub mod storage; pub mod transform; pub(crate) mod utils; -use self::distance::{build_distance_table_l2, compute_l2_distance}; +use self::distance::{build_distance_table_l2, compute_pq_distance}; pub use self::utils::num_centroids; use super::quantizer::{ Quantization, QuantizationMetadata, QuantizationType, Quantizer, QuantizerBuildParams, @@ -267,7 +267,7 @@ impl ProductQuantizer { key.values(), ); - let distances = compute_dot_distance( + let distances = compute_pq_distance( &distance_table, self.num_bits, self.num_sub_vectors, @@ -327,7 +327,7 @@ impl ProductQuantizer { /// The squared L2 distance. #[inline] fn compute_l2_distance(&self, distance_table: &[f32], code: &[u8]) -> Float32Array { - Float32Array::from(compute_l2_distance( + Float32Array::from(compute_pq_distance( distance_table, self.num_bits, self.num_sub_vectors, diff --git a/rust/lance-index/src/vector/pq/distance.rs b/rust/lance-index/src/vector/pq/distance.rs index 8aad9cb3fa..0094d53a4a 100644 --- a/rust/lance-index/src/vector/pq/distance.rs +++ b/rust/lance-index/src/vector/pq/distance.rs @@ -4,7 +4,10 @@ use core::panic; use std::cmp::min; +use itertools::Itertools; use lance_linalg::distance::{dot_distance_batch, l2_distance_batch, Dot, L2}; +use lance_linalg::simd::u8::u8x16; +use lance_linalg::simd::{Shuffle, SIMD}; use lance_table::utils::LanceIteratorExtension; use super::{num_centroids, utils::get_sub_vector_centroids}; @@ -96,14 +99,14 @@ pub fn build_distance_table_dot_impl( /// The squared L2 distance. /// #[inline] -pub(super) fn compute_l2_distance( +pub(super) fn compute_pq_distance( distance_table: &[f32], num_bits: u32, num_sub_vectors: usize, code: &[u8], ) -> Vec { if num_bits == 4 { - return compute_l2_distance_4bit(distance_table, num_sub_vectors, code); + return compute_pq_distance_4bit(distance_table, num_sub_vectors, code); } // here `code` has been transposed, // so code[i][j] is the code of i-th sub-vector of the j-th vector, @@ -129,35 +132,99 @@ pub(super) fn compute_l2_distance( } #[inline] -pub(super) fn compute_l2_distance_4bit( +pub(super) fn compute_pq_distance_4bit( distance_table: &[f32], num_sub_vectors: usize, code: &[u8], ) -> Vec { + let (qmin, qmax, distance_table) = quantize_distance_table(distance_table); let num_vectors = code.len() * 2 / num_sub_vectors; - let mut distances = vec![0.0_f32; num_vectors]; + // store the distances in f32 to avoid overflow + let mut distances = vec![0.0f32; num_vectors]; const NUM_CENTROIDS: usize = 2_usize.pow(4); for (sub_vec_idx, vec_indices) in code.chunks_exact(num_vectors).enumerate() { - let dist_table = - &distance_table[sub_vec_idx * 2 * NUM_CENTROIDS..(sub_vec_idx * 2 + 1) * NUM_CENTROIDS]; - let dist_table_next = &distance_table - [(sub_vec_idx * 2 + 1) * NUM_CENTROIDS..(sub_vec_idx * 2 + 2) * NUM_CENTROIDS]; debug_assert_eq!(vec_indices.len(), distances.len()); - vec_indices - .iter() - .zip(distances.iter_mut()) - .for_each(|(¢roid_idx, sum)| { - // for 4bit PQ, `centroid_idx` is 2 index, each index is 4bit. + let origin_dist_table = unsafe { + u8x16::load_unaligned(distance_table.as_ptr().add(sub_vec_idx * 2 * NUM_CENTROIDS)) + }; + let origin_next_dist_table = unsafe { + u8x16::load_unaligned( + distance_table + .as_ptr() + .add((sub_vec_idx * 2 + 1) * NUM_CENTROIDS), + ) + }; + for i in (0..num_vectors - NUM_CENTROIDS + 1).step_by(NUM_CENTROIDS) { + let vec_indices = unsafe { u8x16::load_unaligned(vec_indices.as_ptr().add(i)) }; + let distances = &mut distances[i..i + NUM_CENTROIDS]; + + // compute current distances + let current_indices = vec_indices.bit_and(0x0F); + let dist_table = origin_dist_table; + let results = dist_table.shuffle(current_indices); + debug_assert_eq!(dist_table.as_array(), origin_dist_table.as_array()); + + // compute next distances + let next_indices = vec_indices.right_shift::<4>(); + let next_dist_table = origin_next_dist_table; + let results = results + next_dist_table.shuffle(next_indices); + + results + .as_array() + .into_iter() + .zip(distances.iter_mut()) + .for_each(|(d, sum)| { + *sum += d as f32; + }); + } + let remainder = num_vectors % NUM_CENTROIDS; + if remainder > 0 { + let vec_indices = &vec_indices[num_vectors - remainder..]; + let distances = &mut distances[num_vectors - remainder..]; + let dist_table = &distance_table[sub_vec_idx * 2 * NUM_CENTROIDS..]; + let next_dist_table = &distance_table[(sub_vec_idx * 2 + 1) * NUM_CENTROIDS..]; + for (i, ¢roid_idx) in vec_indices.iter().enumerate() { let current_idx = centroid_idx & 0xF; let next_idx = centroid_idx >> 4; - *sum += dist_table[current_idx as usize]; - *sum += dist_table_next[next_idx as usize]; - }); + distances[i] += dist_table[current_idx as usize] as f32; + distances[i] += next_dist_table[next_idx as usize] as f32; + } + } } + // need to dequantize the distances + // to make the distances comparable to the others from the other partitions + distances.iter_mut().for_each(|d| { + *d = *d * (qmax - qmin) / 255.0 + qmin; + }); distances } +// Quantize the distance table to u8, +// map distance `d` to `(d-qmin) * 255 / (qmax-qmin)`m +// used for only 4bit PQ so num_centroids must be 16 +// returns (qmin, qmax, quantized_distance_table) +#[inline] +fn quantize_distance_table(distance_table: &[f32]) -> (f32, f32, Vec) { + const NUM_CENTROIDS: usize = 16; + let qmin = distance_table.iter().cloned().fold(f32::INFINITY, f32::min); + let qmax = distance_table + .chunks(NUM_CENTROIDS) + .tuple_windows() + .map(|(a, b)| { + let a_max = a.iter().cloned().fold(f32::NEG_INFINITY, f32::max); + let b_max = b.iter().cloned().fold(f32::NEG_INFINITY, f32::max); + a_max + b_max + }) + .fold(f32::NEG_INFINITY, f32::max); + let quantized_dist_table = distance_table + .iter() + .map(|&d| ((d - qmin) * 255.0 / (qmax - qmin)).ceil() as u8) + .collect(); + + (qmin, qmax, quantized_dist_table) +} + /// Compute L2 distance from the query to all code without transposing the code. /// for testing only /// @@ -201,62 +268,6 @@ fn compute_l2_distance_without_transposing( distances.chain(remainder).collect() } -#[inline] -pub fn compute_dot_distance( - distance_table: &[f32], - num_bits: u32, - num_sub_vectors: usize, - code: &[u8], -) -> Vec { - if num_bits == 4 { - return compute_dot_distance_4bit(distance_table, num_sub_vectors, code); - } - let num_vectors = code.len() / num_sub_vectors; - let mut distances = vec![0.0; num_vectors]; - let num_centroids = num_centroids(num_bits); - for (sub_vec_idx, vec_indices) in code.chunks_exact(num_vectors).enumerate() { - let dist_table = &distance_table[sub_vec_idx * num_centroids..]; - vec_indices - .iter() - .zip(distances.iter_mut()) - .for_each(|(¢roid_idx, sum)| { - *sum += dist_table[centroid_idx as usize]; - }); - } - - distances -} - -#[inline] -pub fn compute_dot_distance_4bit( - distance_table: &[f32], - num_sub_vectors: usize, - code: &[u8], -) -> Vec { - let num_vectors = code.len() * 2 / num_sub_vectors; - let mut distances = vec![0.0; num_vectors]; - const NUM_CENTROIDS: usize = 2_usize.pow(4); - for (sub_vec_idx, vec_indices) in code.chunks_exact(num_vectors).enumerate() { - let dist_table = - &distance_table[sub_vec_idx * 2 * NUM_CENTROIDS..(sub_vec_idx * 2 + 1) * NUM_CENTROIDS]; - let dist_table_next = &distance_table - [(sub_vec_idx * 2 + 1) * NUM_CENTROIDS..(sub_vec_idx * 2 + 2) * NUM_CENTROIDS]; - debug_assert_eq!(vec_indices.len(), distances.len()); - vec_indices - .iter() - .zip(distances.iter_mut()) - .for_each(|(¢roid_idx, sum)| { - // for 4bit PQ, `centroid_idx` is 2 index, each index is 4bit. - let current_idx = centroid_idx & 0xF; - let next_idx = centroid_idx >> 4; - *sum += dist_table[current_idx as usize]; - *sum += dist_table_next[next_idx as usize]; - }); - } - - distances -} - #[cfg(test)] mod tests { use crate::vector::pq::storage::transpose; @@ -278,7 +289,7 @@ mod tests { let pq_codes = Vec::from_iter((0..num_vectors * num_sub_vectors).map(|v| v as u8)); let pq_codes = UInt8Array::from_iter_values(pq_codes); let transposed_codes = transpose(&pq_codes, num_vectors, num_sub_vectors); - let distances = compute_l2_distance( + let distances = compute_pq_distance( &distance_table, num_bits, num_sub_vectors, diff --git a/rust/lance-index/src/vector/pq/storage.rs b/rust/lance-index/src/vector/pq/storage.rs index ef3839aa3e..2ed2681917 100644 --- a/rust/lance-index/src/vector/pq/storage.rs +++ b/rust/lance-index/src/vector/pq/storage.rs @@ -32,8 +32,7 @@ use prost::Message; use serde::{Deserialize, Serialize}; use snafu::{location, Location}; -use super::distance::{build_distance_table_dot, compute_l2_distance}; -use super::distance::{build_distance_table_l2, compute_dot_distance}; +use super::distance::{build_distance_table_dot, build_distance_table_l2, compute_pq_distance}; use super::ProductQuantizer; use crate::vector::storage::STORAGE_METADATA_KEY; use crate::{ @@ -626,7 +625,7 @@ impl DistCalculator for PQDistCalculator { fn distance_all(&self) -> Vec { match self.distance_type { - DistanceType::L2 => compute_l2_distance( + DistanceType::L2 => compute_pq_distance( &self.distance_table, self.num_bits, self.num_sub_vectors, @@ -642,7 +641,7 @@ impl DistCalculator for PQDistCalculator { // L2 over normalized vectors: ||x - y|| = x^2 + y^2 - 2 * xy = 1 + 1 - 2 * xy = 2 * (1 - xy) // Cosine distance: 1 - |xy| / (||x|| * ||y||) = 1 - xy / (x^2 * y^2) = 1 - xy / (1 * 1) = 1 - xy // Therefore, Cosine = L2 / 2 - let l2_dists = compute_l2_distance( + let l2_dists = compute_pq_distance( &self.distance_table, self.num_bits, self.num_sub_vectors, @@ -650,7 +649,7 @@ impl DistCalculator for PQDistCalculator { ); l2_dists.into_iter().map(|v| v / 2.0).collect() } - DistanceType::Dot => compute_dot_distance( + DistanceType::Dot => compute_pq_distance( &self.distance_table, self.num_bits, self.num_sub_vectors, diff --git a/rust/lance-linalg/src/simd.rs b/rust/lance-linalg/src/simd.rs index da4429a251..dc3b6b680e 100644 --- a/rust/lance-linalg/src/simd.rs +++ b/rust/lance-linalg/src/simd.rs @@ -16,8 +16,10 @@ use std::ops::{Add, AddAssign, Mul, Sub, SubAssign}; pub mod f32; pub mod i32; +pub mod u8; use num_traits::{Float, Num}; +use u8::u8x16; /// Lance SIMD lib /// @@ -93,3 +95,7 @@ pub trait FloatSimd: SIMD { /// c = a * b + c fn multiply_add(&mut self, a: Self, b: Self); } + +pub trait Shuffle { + fn shuffle(&self, indices: u8x16) -> Self; +} diff --git a/rust/lance-linalg/src/simd/u8.rs b/rust/lance-linalg/src/simd/u8.rs new file mode 100644 index 0000000000..6a0449739b --- /dev/null +++ b/rust/lance-linalg/src/simd/u8.rs @@ -0,0 +1,427 @@ +// SPDX-License-Identifier: Apache-2.0 +// SPDX-FileCopyrightText: Copyright The Lance Authors + +//! `u8x8`, 8 of `u8` values + +use std::fmt::Formatter; + +#[cfg(target_arch = "aarch64")] +use std::arch::aarch64::*; +#[cfg(target_arch = "x86_64")] +use std::arch::x86_64::*; +use std::ops::{Add, AddAssign, Mul, Sub, SubAssign}; + +use super::{Shuffle, SIMD}; + +/// 16 of 8-bit `u8` values. +#[allow(non_camel_case_types)] +#[cfg(target_arch = "x86_64")] +#[derive(Clone, Copy)] +pub struct u8x16(pub __m128i); + +/// 16 of 8-bit `u8` values. +#[allow(non_camel_case_types)] +#[cfg(target_arch = "aarch64")] +#[derive(Clone, Copy)] +pub struct u8x16(pub uint8x16_t); + +#[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] +#[derive(Clone, Copy)] +pub struct u8x16(pub [u8; 16]); + +impl u8x16 { + #[inline] + pub fn bit_and(self, mask: u8) -> Self { + #[cfg(target_arch = "x86_64")] + unsafe { + Self(_mm_and_si128(self.0, _mm_set1_epi8(mask as i8))) + } + #[cfg(target_arch = "aarch64")] + unsafe { + Self(vandq_u8(self.0, vdupq_n_u8(mask))) + } + #[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] + { + for i in 0..16 { + self.0[i] &= mask; + } + } + } + + #[inline] + pub fn right_shift(self) -> Self { + #[cfg(target_arch = "x86_64")] + unsafe { + let shifted = _mm_srli_epi16(self.0, N); + let mask = _mm_set1_epi8((1_i8 << (8 - N)) - 1); + Self(_mm_and_si128(shifted, mask)) + } + #[cfg(target_arch = "aarch64")] + unsafe { + Self(vshrq_n_u8::(self.0)) + } + #[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] + { + let mut result = [0u8; 16]; + for i in 0..16 { + result[i] = self.0[i] >> N; + } + Self(result) + } + } +} + +impl std::fmt::Debug for u8x16 { + fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result { + let mut arr = [0u8; 16]; + unsafe { + self.store_unaligned(arr.as_mut_ptr()); + } + write!(f, "u8x16({:?})", arr) + } +} + +impl From<&[u8]> for u8x16 { + fn from(value: &[u8]) -> Self { + unsafe { Self::load_unaligned(value.as_ptr()) } + } +} + +impl<'a> From<&'a [u8; 16]> for u8x16 { + fn from(value: &'a [u8; 16]) -> Self { + unsafe { Self::load_unaligned(value.as_ptr()) } + } +} + +impl SIMD for u8x16 { + #[inline] + fn splat(val: u8) -> Self { + #[cfg(target_arch = "x86_64")] + unsafe { + Self(_mm_set1_epi8(val as i8)) + } + #[cfg(target_arch = "aarch64")] + unsafe { + Self(vdupq_n_u8(val)) + } + #[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] + { + let mut result = [0u8; 16]; + for i in 0..16 { + result[i] = val; + } + Self(result) + } + } + + #[inline] + fn zeros() -> Self { + #[cfg(target_arch = "x86_64")] + unsafe { + Self(_mm_setzero_si128()) + } + #[cfg(target_arch = "aarch64")] + { + Self::splat(0) + } + #[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] + { + Self([0; 16]) + } + } + + #[inline] + unsafe fn load(ptr: *const u8) -> Self { + #[cfg(target_arch = "x86_64")] + unsafe { + Self(_mm_loadu_si128(ptr as *const __m128i)) + } + #[cfg(target_arch = "aarch64")] + { + Self::load_unaligned(ptr) + } + #[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] + { + Self::load_unaligned(ptr) + } + } + + #[inline] + unsafe fn load_unaligned(ptr: *const u8) -> Self { + #[cfg(target_arch = "x86_64")] + unsafe { + Self(_mm_loadu_si128(ptr as *const __m128i)) + } + #[cfg(target_arch = "aarch64")] + { + Self(vld1q_u8(ptr)) + } + #[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] + { + let mut result = [0u8; 16]; + for i in 0..16 { + result[i] = *ptr.add(i); + } + Self(result) + } + } + + #[inline] + unsafe fn store(&self, ptr: *mut u8) { + #[cfg(target_arch = "x86_64")] + unsafe { + _mm_storeu_si128(ptr as *mut __m128i, self.0) + } + #[cfg(target_arch = "aarch64")] + unsafe { + vst1q_u8(ptr, self.0) + } + #[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] + { + self.store_unaligned(ptr); + } + } + + #[inline] + unsafe fn store_unaligned(&self, ptr: *mut u8) { + #[cfg(target_arch = "x86_64")] + unsafe { + _mm_storeu_si128(ptr as *mut __m128i, self.0) + } + #[cfg(target_arch = "aarch64")] + unsafe { + vst1q_u8(ptr, self.0) + } + #[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] + { + for i in 0..16 { + *ptr.add(i) = self.0[i]; + } + } + } + + fn reduce_sum(&self) -> u8 { + todo!("it is not implemented yet"); + } + + #[inline] + fn reduce_min(&self) -> u8 { + #[cfg(target_arch = "x86_64")] + unsafe { + let low = _mm_and_si128(self.0, _mm_set1_epi8(0xFF_u8 as i8)); + let high = _mm_srli_si128(self.0, 8); + let min_low = _mm_min_epu8(low, high); + let min_low = _mm_min_epu8(min_low, _mm_srli_si128(min_low, 4)); + let min_low = _mm_min_epu8(min_low, _mm_srli_si128(min_low, 2)); + let min_low = _mm_min_epu8(min_low, _mm_srli_si128(min_low, 1)); + _mm_extract_epi8(min_low, 0) as u8 + } + #[cfg(target_arch = "aarch64")] + unsafe { + vminvq_u8(self.0) + } + #[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] + { + let mut min = self.0[0]; + for i in 1..16 { + min = std::cmp::min(min, self.0[i]); + } + min + } + } + + #[inline] + fn min(&self, rhs: &Self) -> Self { + #[cfg(target_arch = "x86_64")] + unsafe { + Self(_mm_min_epu8(self.0, rhs.0)) + } + #[cfg(target_arch = "aarch64")] + unsafe { + Self(vminq_u8(self.0, rhs.0)) + } + #[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] + { + let mut result = [0u8; 16]; + for i in 0..16 { + result[i] = std::cmp::min(self.0[i], rhs.0[i]); + } + Self(result) + } + } + + fn find(&self, _val: u8) -> Option { + todo!() + } +} + +impl Shuffle for u8x16 { + fn shuffle(&self, indices: u8x16) -> Self { + #[cfg(target_arch = "x86_64")] + unsafe { + Self(_mm_shuffle_epi8(self.0, indices.0)) + } + #[cfg(target_arch = "aarch64")] + unsafe { + Self(vqtbl1q_u8(self.0, indices.0)) + } + #[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] + { + let mut result = [0u8; 16]; + for i in 0..16 { + result[i] = self.0[indices.0[i] as usize]; + } + Self(result) + } + } +} + +impl Add for u8x16 { + type Output = Self; + + #[inline] + fn add(self, rhs: Self) -> Self::Output { + #[cfg(target_arch = "x86_64")] + unsafe { + Self(_mm_add_epi8(self.0, rhs.0)) + } + #[cfg(target_arch = "aarch64")] + unsafe { + Self(vqaddq_u8(self.0, rhs.0)) + } + #[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] + { + let mut result = [0u8; 16]; + for i in 0..16 { + result[i] = self.0[i].saturating_add(rhs.0[i]); + } + Self(result) + } + } +} + +impl AddAssign for u8x16 { + #[inline] + fn add_assign(&mut self, rhs: Self) { + #[cfg(target_arch = "x86_64")] + unsafe { + self.0 = _mm_add_epi8(self.0, rhs.0) + } + #[cfg(target_arch = "aarch64")] + unsafe { + self.0 = vaddq_u8(self.0, rhs.0) + } + #[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] + { + for i in 0..16 { + self.0[i] = self.0[i].saturating_add(rhs.0[i]); + } + } + } +} + +impl Mul for u8x16 { + type Output = Self; + + #[inline] + fn mul(self, rhs: Self) -> Self::Output { + #[cfg(target_arch = "x86_64")] + unsafe { + let a_lo = _mm_unpacklo_epi8(self.0, _mm_setzero_si128()); + let a_hi = _mm_unpackhi_epi8(self.0, _mm_setzero_si128()); + let b_lo = _mm_unpacklo_epi8(rhs.0, _mm_setzero_si128()); + let b_hi = _mm_unpackhi_epi8(rhs.0, _mm_setzero_si128()); + + let res_lo = _mm_mullo_epi16(a_lo, b_lo); + let res_hi = _mm_mullo_epi16(a_hi, b_hi); + + Self(_mm_packus_epi16(res_lo, res_hi)) + } + #[cfg(target_arch = "aarch64")] + unsafe { + Self(vmulq_u8(self.0, rhs.0)) + } + #[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] + { + let mut result = [0u8; 16]; + for i in 0..16 { + result[i] = self.0[i].wrapping_mul(rhs.0[i]); + } + Self(result) + } + } +} + +impl Sub for u8x16 { + type Output = Self; + + #[inline] + fn sub(self, rhs: Self) -> Self::Output { + #[cfg(target_arch = "x86_64")] + unsafe { + Self(_mm_sub_epi8(self.0, rhs.0)) + } + #[cfg(target_arch = "aarch64")] + unsafe { + Self(vsubq_u8(self.0, rhs.0)) + } + #[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] + { + let mut result = [0u8; 16]; + for i in 0..16 { + result[i] = self.0[i].wrapping_sub(rhs.0[i]); + } + Self(result) + } + } +} + +impl SubAssign for u8x16 { + #[inline] + fn sub_assign(&mut self, rhs: Self) { + #[cfg(target_arch = "x86_64")] + unsafe { + self.0 = _mm_sub_epi8(self.0, rhs.0) + } + #[cfg(target_arch = "aarch64")] + unsafe { + self.0 = vsubq_u8(self.0, rhs.0) + } + #[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))] + { + for i in 0..16 { + self.0[i] = self.0[i].wrapping_sub(rhs.0[i]); + } + } + } +} + +#[cfg(test)] +mod tests { + + use super::*; + + #[test] + fn test_basic_u8x16_ops() { + let a = (0..16).map(|f| f as u8).collect::>(); + let b = (16..32).map(|f| f as u8).collect::>(); + + let simd_a = unsafe { u8x16::load_unaligned(a.as_ptr()) }; + let simd_b = unsafe { u8x16::load_unaligned(b.as_ptr()) }; + + let simd_add = simd_a + simd_b; + (0..16) + .zip(simd_add.as_array().iter()) + .for_each(|(x, &y)| assert_eq!((x + x + 16) as u8, y)); + + // on x86_64, the result of simd_mul is saturated + // on aarch64, the result of simd_mul is not saturated + let simd_mul = simd_a * simd_b; + (0..16).zip(simd_mul.as_array().iter()).for_each(|(x, &y)| { + #[cfg(target_arch = "x86_64")] + assert_eq!(std::cmp::min(x * (x + 16), 255_i32) as u8, y); + #[cfg(target_arch = "aarch64")] + assert_eq!((x * (x + 16_i32)) as u8, y); + }); + } +} diff --git a/rust/lance/src/index/vector/ivf/v2.rs b/rust/lance/src/index/vector/ivf/v2.rs index 727f50ecea..f518d41bfc 100644 --- a/rust/lance/src/index/vector/ivf/v2.rs +++ b/rust/lance/src/index/vector/ivf/v2.rs @@ -532,6 +532,7 @@ mod tests { use lance_index::vector::DIST_COL; use lance_index::{DatasetIndexExt, IndexType}; use lance_linalg::distance::DistanceType; + use lance_linalg::kernels::normalize_arrow; use lance_testing::datagen::generate_random_array_with_range; use rstest::rstest; use tempfile::tempdir; @@ -545,6 +546,7 @@ mod tests { range: Range, ) -> (Dataset, Arc) { let vectors = generate_random_array_with_range::(1000 * DIM, range); + let vectors = normalize_arrow(&vectors).unwrap(); let metadata: HashMap = vec![("test".to_string(), "ivf_pq".to_string())] .into_iter() .collect();