Skip to content

Actions: ggerganov/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
9,058 workflow runs
9,058 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

server : POC OAI-compat TTS using OuteTTS Server #9490: Pull request #11070 synchronize by ngxson
January 4, 2025 11:38 6m 41s ngxson:xsn/server_tts
ngxson:xsn/server_tts
January 4, 2025 11:38 6m 41s
server : POC OAI-compat TTS using OuteTTS Server #9489: Pull request #11070 synchronize by ngxson
January 4, 2025 11:11 6m 23s ngxson:xsn/server_tts
ngxson:xsn/server_tts
January 4, 2025 11:11 6m 23s
sync : ggml Server #9488: Pull request #11075 opened by ggerganov
January 4, 2025 08:54 49m 51s sync-ggml-25-01-04-0
sync-ggml-25-01-04-0
January 4, 2025 08:54 49m 51s
Vulkan: Add device-specific blacklist for coopmat for the AMD proprietary driver Server #9487: Pull request #11074 opened by 0cc4m
January 4, 2025 08:52 36m 11s 0cc4m/coopmat-blacklist
0cc4m/coopmat-blacklist
January 4, 2025 08:52 36m 11s
fix: Vulkan shader gen binary path (#11037) Server #9486: Commit c31fc8b pushed by 0cc4m
January 4, 2025 08:17 17m 8s master
master
January 4, 2025 08:17 17m 8s
[GGML][RPC] Support for models with non-512-aligned tensors over RPC. Server #9485: Pull request #11047 synchronize by matt23654
January 3, 2025 22:46 15m 1s matt23654:rpc-experimental
matt23654:rpc-experimental
January 3, 2025 22:46 15m 1s
server : POC OAI-compat TTS using OuteTTS Server #9484: Pull request #11070 opened by ngxson
January 3, 2025 22:42 5m 23s ngxson:xsn/server_tts
ngxson:xsn/server_tts
January 3, 2025 22:42 5m 23s
[GGML][RPC] Support for models with non-512-aligned tensors over RPC. Server #9483: Pull request #11047 synchronize by matt23654
January 3, 2025 22:17 17m 28s matt23654:rpc-experimental
matt23654:rpc-experimental
January 3, 2025 22:17 17m 28s
Add support for DeepSeek V3 Server #9482: Pull request #11049 synchronize by fairydreaming
January 3, 2025 21:15 11m 30s fairydreaming:deepseek-v3
fairydreaming:deepseek-v3
January 3, 2025 21:15 11m 30s
GGUF: C++ refactor, backend support, misc fixes Server #9481: Pull request #11030 synchronize by JohannesGaessler
January 3, 2025 14:47 15m 41s JohannesGaessler:gguf-refactor-7
JohannesGaessler:gguf-refactor-7
January 3, 2025 14:47 15m 41s
GGUF: C++ refactor, backend support, misc fixes Server #9480: Pull request #11030 synchronize by JohannesGaessler
January 3, 2025 14:41 5m 55s JohannesGaessler:gguf-refactor-7
JohannesGaessler:gguf-refactor-7
January 3, 2025 14:41 5m 55s
GGUF: C++ refactor, backend support, misc fixes Server #9478: Pull request #11030 synchronize by JohannesGaessler
January 3, 2025 14:35 5m 50s JohannesGaessler:gguf-refactor-7
JohannesGaessler:gguf-refactor-7
January 3, 2025 14:35 5m 50s
llama : add support for Cohere2ForCausalLM Server #9477: Pull request #10900 synchronize by dranger003
January 3, 2025 13:43 1h 0m 16s dranger003:cohere2
dranger003:cohere2
January 3, 2025 13:43 1h 0m 16s
llama : remove notion of CLS token Server #9476: Pull request #11064 opened by ggerganov
January 3, 2025 12:54 1h 39m 11s gg/llama-refactor-5
gg/llama-refactor-5
January 3, 2025 12:54 1h 39m 11s
llama : update llama_model API names Server #9475: Pull request #11063 opened by ggerganov
January 3, 2025 12:44 1h 35m 1s gg/llama-refactor-4
gg/llama-refactor-4
January 3, 2025 12:44 1h 35m 1s
llama : use LLAMA_TOKEN_NULL Server #9474: Pull request #11062 opened by ggerganov
January 3, 2025 12:28 1h 29m 11s gg/llama-refactor-3
gg/llama-refactor-3
January 3, 2025 12:28 1h 29m 11s
common : disable KV cache shifting automatically for unsupported mode… Server #9473: Commit 4b0c638 pushed by ggerganov
January 3, 2025 12:13 42m 19s master
master
January 3, 2025 12:13 42m 19s
llama : avoid hardcoded QK_K constant Server #9472: Pull request #11061 opened by ggerganov
January 3, 2025 12:08 23m 16s gg/llama-refactor-2
gg/llama-refactor-2
January 3, 2025 12:08 23m 16s
Disable KV cache shifting automatically for unsupported models Server #9471: Pull request #11053 synchronize by MollySophia
January 3, 2025 12:06 5m 21s MollySophia:context-shift
MollySophia:context-shift
January 3, 2025 12:06 5m 21s
llama : use _impl suffix instead of _internal Server #9470: Pull request #11060 opened by ggerganov
January 3, 2025 11:55 9m 20s gg/llama-refactor-1
gg/llama-refactor-1
January 3, 2025 11:55 9m 20s
android : Apply chat template Server #9469: Pull request #11059 opened by Dhruvanand24
January 3, 2025 10:54 6m 10s Dhruvanand24:Apply_chat_template
Dhruvanand24:Apply_chat_template
January 3, 2025 10:54 6m 10s
tokenize : escape the prompt Server #9468: Pull request #11058 opened by ggerganov
January 3, 2025 10:07 6m 0s gg/tokenize-escape
gg/tokenize-escape
January 3, 2025 10:07 6m 0s
metal : avoid uint (#11019) Server #9467: Commit e7da954 pushed by ggerganov
January 3, 2025 09:26 15m 2s master
master
January 3, 2025 09:26 15m 2s
Add support for QRWKV6 hybrid models & slight optimization for RWKV6 Server #9466: Pull request #11001 synchronize by MollySophia
January 3, 2025 09:21 6m 6s MollySophia:rwkv6qwen2
MollySophia:rwkv6qwen2
January 3, 2025 09:21 6m 6s
Disable KV cache shifting automatically for unsupported models Server #9465: Pull request #11053 opened by MollySophia
January 3, 2025 08:36 4m 46s MollySophia:context-shift
MollySophia:context-shift
January 3, 2025 08:36 4m 46s