Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Bug]: Gemma-2 + FlashInfer: ValueError: Unsupported max_frags_z: #6395

Closed
HanGuo97 opened this issue Jul 12, 2024 · 5 comments
Closed

[Bug]: Gemma-2 + FlashInfer: ValueError: Unsupported max_frags_z: #6395

HanGuo97 opened this issue Jul 12, 2024 · 5 comments
Labels
bug Something isn't working stale

Comments

@HanGuo97
Copy link

Your current environment

PyTorch version: 2.3.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.3 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.26.4
Libc version: glibc-2.35

Python version: 3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.4.0-186-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.1.105
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: 
GPU 0: NVIDIA RTX A6000
GPU 1: NVIDIA RTX A6000

Nvidia driver version: 525.147.05
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.0
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Architecture:                       x86_64
CPU op-mode(s):                     32-bit, 64-bit
Address sizes:                      46 bits physical, 48 bits virtual
Byte Order:                         Little Endian
CPU(s):                             80
On-line CPU(s) list:                0-79
Vendor ID:                          GenuineIntel
Model name:                         Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz
CPU family:                         6
Model:                              85
Thread(s) per core:                 2
Core(s) per socket:                 20
Socket(s):                          2
Stepping:                           7
CPU max MHz:                        4000.0000
CPU min MHz:                        800.0000
BogoMIPS:                           4200.00
Flags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single intel_ppin ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req pku ospke avx512_vnni md_clear flush_l1d arch_capabilities
Virtualization:                     VT-x
L1d cache:                          1.3 MiB (40 instances)
L1i cache:                          1.3 MiB (40 instances)
L2 cache:                           40 MiB (40 instances)
L3 cache:                           55 MiB (2 instances)
NUMA node(s):                       2
NUMA node0 CPU(s):                  0-19,40-59
NUMA node1 CPU(s):                  20-39,60-79
Vulnerability Gather data sampling: Mitigation; Microcode
Vulnerability Itlb multihit:        KVM: Mitigation: Split huge pages
Vulnerability L1tf:                 Not affected
Vulnerability Mds:                  Not affected
Vulnerability Meltdown:             Not affected
Vulnerability Mmio stale data:      Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Retbleed:             Mitigation; Enhanced IBRS
Vulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:           Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
Vulnerability Srbds:                Not affected
Vulnerability Tsx async abort:      Mitigation; TSX disabled

Versions of relevant libraries:
[pip3] flashinfer==0.0.9+cu121torch2.3
[pip3] numpy==1.26.4
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] optree==0.11.0
[pip3] torch==2.3.0
[pip3] torchaudio==2.2.2
[pip3] torchelastic==0.2.2
[pip3] torchvision==0.18.0
[pip3] transformers==4.42.3
[pip3] triton==2.3.0
[conda] blas                      1.0                         mkl  
[conda] ffmpeg                    4.3                  hf484d3e_0    pytorch
[conda] libjpeg-turbo             2.0.0                h9bf148f_0    pytorch
[conda] mkl                       2023.1.0         h213fc3f_46344  
[conda] mkl-service               2.4.0           py310h5eee18b_1  
[conda] mkl_fft                   1.3.8           py310h5eee18b_0  
[conda] mkl_random                1.2.4           py310hdb19cb5_0  
[conda] numpy                     1.26.4          py310h5f9d8c6_0  
[conda] numpy-base                1.26.4          py310hb5e798b_0  
[conda] optree                    0.11.0                   pypi_0    pypi
[conda] pytorch                   2.2.2           py3.10_cuda12.1_cudnn8.9.2_0    pytorch
[conda] pytorch-cuda              12.1                 ha16c6d3_5    pytorch
[conda] pytorch-mutex             1.0                        cuda    pytorch
[conda] torchaudio                2.2.2               py310_cu121    pytorch
[conda] torchelastic              0.2.2                    pypi_0    pypi
[conda] torchtriton               2.2.0                     py310    pytorch
[conda] torchvision               0.17.2              py310_cu121    pytorch
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.5.1
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0    GPU1    CPU Affinity    NUMA Affinity
GPU0     X      PIX     0-19,40-59      0
GPU1    PIX      X      0-19,40-59      0

Legend:

  X    = Self
  SYS  = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
  NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
  PHB  = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
  PXB  = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
  PIX  = Connection traversing at most a single PCIe bridge
  NV#  = Connection traversing a bonded set of # NVLinks

🐛 Describe the bug

The following script will fail using Gemma-2 9B (27B works fine), and with small input length (1,2 will fail, 32 works).

VLLM_ATTENTION_BACKEND=FLASHINFER python benchmark_latency.py \
    --model google/gemma-2-9b-it \
    --tokenizer google/gemma-2-9b-it \
    --input-len 1 \
    --output-len 128 \
    --batch-size 1 \
    --dtype "float16"

The error message (coming from flashinfer) is:

...
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/vllm/utils.py", line 795, in inner
[rank0]:     return fn(*args, **kwargs)
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/vllm/entrypoints/llm.py", line 309, in generate
[rank0]:     outputs = self._run_engine(use_tqdm=use_tqdm)
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/vllm/entrypoints/llm.py", line 561, in _run_engine
[rank0]:     step_outputs = self.llm_engine.step()
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 861, in step
[rank0]:     output = self.model_executor.execute_model(
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/vllm/executor/gpu_executor.py", line 92, in execute_model
[rank0]:     output = self.driver_worker.execute_model(execute_model_req)
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/vllm/worker/worker_base.py", line 271, in execute_model
[rank0]:     output = self.model_runner.execute_model(
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
[rank0]:     return func(*args, **kwargs)
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/vllm/worker/model_runner.py", line 1243, in execute_model
[rank0]:     hidden_or_intermediate_states = model_executable(
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[rank0]:     return self._call_impl(*args, **kwargs)
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[rank0]:     return forward_call(*args, **kwargs)
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/vllm/model_executor/models/gemma2.py", line 336, in forward
[rank0]:     hidden_states = self.model(input_ids, positions, kv_caches,
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[rank0]:     return self._call_impl(*args, **kwargs)
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[rank0]:     return forward_call(*args, **kwargs)
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/vllm/model_executor/models/gemma2.py", line 277, in forward
[rank0]:     hidden_states, residual = layer(
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[rank0]:     return self._call_impl(*args, **kwargs)
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[rank0]:     return forward_call(*args, **kwargs)
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/vllm/model_executor/models/gemma2.py", line 221, in forward
[rank0]:     hidden_states = self.self_attn(
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[rank0]:     return self._call_impl(*args, **kwargs)
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[rank0]:     return forward_call(*args, **kwargs)
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/vllm/model_executor/models/gemma2.py", line 162, in forward
[rank0]:     attn_output = self.attn(q, k, v, kv_cache, attn_metadata)
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[rank0]:     return self._call_impl(*args, **kwargs)
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[rank0]:     return forward_call(*args, **kwargs)
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/vllm/attention/layer.py", line 94, in forward
[rank0]:     return self.impl.forward(query, key, value, kv_cache, attn_metadata,
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/vllm/attention/backends/flashinfer.py", line 276, in forward
[rank0]:     output = prefill_meta.prefill_wrapper.forward(
[rank0]:   File "/workspace/main/.local/lib/python3.10/site-packages/flashinfer/prefill.py", line 875, in forward
[rank0]:     return self._wrapper.forward(
[rank0]: ValueError: Unsupported max_frags_z: 0
@HanGuo97 HanGuo97 added the bug Something isn't working label Jul 12, 2024
@exceedzhang
Copy link

exceedzhang commented Jul 20, 2024 •
edited
Loading

image

same error!

@yzh119
Copy link

yzh119 commented Jul 20, 2024

This is due to the small shared memory size of RTX A6000 (sm86), I will fix it in flashinfer v0.1.1 release, thanks for reporting.

@yzh119 yzh119 mentioned this issue Jul 20, 2024
Merged
yzh119 added a commit to flashinfer-ai/flashinfer that referenced this issue Jul 20, 2024
@yzh119
bugfix: Fix invalid kernel configuration for sm86 (#385)
cdac577 
Related issue: vllm-project/vllm#6395
@exceedzhang
Copy link

It work well! @yzh119 Thanks

@github-actions GitHub Actions
Copy link

This issue has been automatically marked as stale because it has not had any activity within 90 days. It will be automatically closed if no further activity occurs within 30 days. Leave a comment if you feel this issue should remain open. Thank you!

@github-actions github-actions bot added the stale label Oct 25, 2024
@github-actions GitHub Actions
Copy link

This issue has been automatically closed due to inactivity. Please feel free to reopen if you feel it is still relevant. Thank you!

@github-actions github-actions bot closed this as not planned Won't fix, can't repro, duplicate, stale Nov 24, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
bug Something isn't working stale
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@exceedzhang @yzh119 @HanGuo97