vllm: [Bug]: segfault when loading MoE models
Your current environment
Anything you want to discuss about vllm.
Your current environment
The output of `python collect_env.py`
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.4 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.30.2
Libc version: glibc-2.35
Python version: 3.11.0rc1 (main, Aug 12 2022, 10:02:14) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.15.0-1065-aws-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA L4
GPU 1: NVIDIA L4
GPU 2: NVIDIA L4
GPU 3: NVIDIA L4
GPU 4: NVIDIA L4
GPU 5: NVIDIA L4
GPU 6: NVIDIA L4
GPU 7: NVIDIA L4
Nvidia driver version: 535.161.07
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.7
/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.7
/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.7
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.7
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.7
/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.7
/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.7
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: 48 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 192
On-line CPU(s) list: 0-191
Vendor ID: AuthenticAMD
Model name: AMD EPYC 7R13 Processor
CPU family: 25
Model: 1
Thread(s) per core: 2
Core(s) per socket: 48
Socket(s): 2
Stepping: 1
BogoMIPS: 5299.99
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf tsc_known_freq pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch topoext perfctr_core invpcid_single ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru wbnoinvd arat npt nrip_save vaes vpclmulqdq rdpid
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 3 MiB (96 instances)
L1i cache: 3 MiB (96 instances)
L2 cache: 48 MiB (96 instances)
L3 cache: 384 MiB (12 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-47,96-143
NUMA node1 CPU(s): 48-95,144-191
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Mitigation; safe RET, no microcode
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; Retpolines; IBPB conditional; IBRS_FW; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] mypy-extensions==0.4.3
[pip3] numpy==1.23.5
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] optree==0.12.1
[pip3] pyzmq==23.2.0
[pip3] sentence-transformers==2.7.0
[pip3] torch==2.4.0
[pip3] torcheval==0.0.7
[pip3] torchvision==0.19.0
[pip3] transformers==4.44.0
[pip3] triton==3.0.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.5.4@4db5176d9758b720b05460c50ace3c01026eb158
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NODE NODE NODE SYS SYS SYS SYS 0-47,96-143 0 N/A
GPU1 NODE X NODE NODE SYS SYS SYS SYS 0-47,96-143 0 N/A
GPU2 NODE NODE X NODE SYS SYS SYS SYS 0-47,96-143 0 N/A
GPU3 NODE NODE NODE X SYS SYS SYS SYS 0-47,96-143 0 N/A
GPU4 SYS SYS SYS SYS X NODE NODE NODE 48-95,144-191 1 N/A
GPU5 SYS SYS SYS SYS NODE X NODE NODE 48-95,144-191 1 N/A
GPU6 SYS SYS SYS SYS NODE NODE X NODE 48-95,144-191 1 N/A
GPU7 SYS SYS SYS SYS NODE NODE NODE X 48-95,144-191 1 N/A
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
🐛 Describe the bug
Cannot run mixtral 8x7b
INFO 08-20 20:23:00 api_server.py:212] vLLM API server version 0.5.2
INFO 08-20 20:23:00 api_server.py:213] args: Namespace(model_tag='mistralai/Mixtral-8x7B-Instruct-v0.1/', host='0.0.0.0', port=1234, uvicorn_log_level='info', allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key=None, lora_modules=None, prompt_adapters=None, chat_template=None, response_role='assistant', ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, ssl_cert_reqs=0, root_path=None, middleware=[], model='mistralai/Mixtral-8x7B-Instruct-v0.1/', tokenizer=None, skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='auto', trust_remote_code=False, download_dir=None, load_format='auto', dtype='auto', kv_cache_dtype='auto', quantization_param_path=None, max_model_len=8192, guided_decoding_backend='outlines', distributed_executor_backend='ray', worker_use_ray=False, pipeline_parallel_size=1, tensor_parallel_size=8, max_parallel_loading_workers=None, ray_workers_use_nsight=False, block_size=16, enable_prefix_caching=False, disable_sliding_window=False, use_v2_block_manager=False, num_lookahead_slots=0, seed=0, swap_space=4, gpu_memory_utilization=0.9, num_gpu_blocks_override=None, max_num_batched_tokens=None, max_num_seqs=256, max_logprobs=20, disable_log_stats=False, quantization=None, rope_scaling=None, rope_theta=None, enforce_eager=False, max_context_len_to_capture=None, max_seq_len_to_capture=8192, disable_custom_all_reduce=False, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config=None, enable_lora=False, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype='auto', long_lora_scaling_factors=None, max_cpu_loras=None, fully_sharded_loras=False, enable_prompt_adapter=False, max_prompt_adapters=1, max_prompt_adapter_token=0, device='auto', scheduler_delay_factor=0.0, enable_chunked_prefill=False, speculative_model=None, num_speculative_tokens=None, speculative_draft_tensor_parallel_size=None, speculative_max_model_len=None, speculative_disable_by_batch_size=None, ngram_prompt_lookup_max=None, ngram_prompt_lookup_min=None, spec_decoding_acceptance_method='rejection_sampler', typical_acceptance_sampler_posterior_threshold=None, typical_acceptance_sampler_posterior_alpha=None, model_loader_extra_config=None, preemption_mode=None, served_model_name=['mixtral-8x7b-instruct-v0.1'], qlora_adapter_name_or_path=None, otlp_traces_endpoint=None, engine_use_ray=False, disable_log_requests=False, max_log_len=None, dispatch_function=<function serve at 0x7fc892b21800>)
2024-08-20 20:23:02,965 INFO worker.py:1740 -- Started a local Ray instance. View the dashboard at 127.0.0.1:8265
INFO 08-20 20:23:11 llm_engine.py:174] Initializing an LLM engine (v0.5.2) with config: model='/dbfs/mnt/dna_pai_tvc/nbilla/hf_cache/mistralai/Mixtral-8x7B-Instruct-v0.1/', speculative_config=None, tokenizer='/dbfs/mnt/dna_pai_tvc/nbilla/hf_cache/mistralai/Mixtral-8x7B-Instruct-v0.1/', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, rope_scaling=None, rope_theta=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=8192, download_dir=None, load_format=LoadFormat.AUTO, tensor_parallel_size=8, pipeline_parallel_size=1, disable_custom_all_reduce=False, quantization=None, enforce_eager=False, kv_cache_dtype=auto, quantization_param_path=None, device_config=cuda, decoding_config=DecodingConfig(guided_decoding_backend='outlines'), observability_config=ObservabilityConfig(otlp_traces_endpoint=None), seed=0, served_model_name=mixtral-8x7b-instruct-v0.1, use_v2_block_manager=False, enable_prefix_caching=False)
INFO 08-20 20:23:37 utils.py:737] Found nccl from library libnccl.so.2
INFO 08-20 20:23:37 pynccl.py:63] vLLM is using nccl==2.22.3
(RayWorkerWrapper pid=141052) INFO 08-20 20:23:37 utils.py:737] Found nccl from library libnccl.so.2
(RayWorkerWrapper pid=141052) INFO 08-20 20:23:37 pynccl.py:63] vLLM is using nccl==2.22.3
WARNING 08-20 20:23:37 custom_all_reduce.py:118] Custom allreduce is disabled because it's not supported on more than two PCIe-only GPUs. To silence this warning, specify disable_custom_all_reduce=True explicitly.
(RayWorkerWrapper pid=141052) WARNING 08-20 20:23:37 custom_all_reduce.py:118] Custom allreduce is disabled because it's not supported on more than two PCIe-only GPUs. To silence this warning, specify disable_custom_all_reduce=True explicitly.
INFO 08-20 20:23:44 model_runner.py:266] Loading model weights took 10.8853 GB
(RayWorkerWrapper pid=141052) INFO 08-20 20:23:45 model_runner.py:266] Loading model weights took 10.8853 GB
(RayWorkerWrapper pid=142816) INFO 08-20 20:23:37 utils.py:737] Found nccl from library libnccl.so.2 [repeated 6x across cluster] (Ray deduplicates logs by default. Set RAY_DEDUP_LOGS=0 to disable log deduplication, or see https://docs.ray.io/en/master/ray-observability/user-guides/configure-logging.html#log-deduplication for more options.)
(RayWorkerWrapper pid=142816) INFO 08-20 20:23:37 pynccl.py:63] vLLM is using nccl==2.22.3 [repeated 6x across cluster]
(RayWorkerWrapper pid=142816) WARNING 08-20 20:23:37 custom_all_reduce.py:118] Custom allreduce is disabled because it's not supported on more than two PCIe-only GPUs. To silence this warning, specify disable_custom_all_reduce=True explicitly. [repeated 6x across cluster]
*** SIGSEGV received at time=1724185428 on cpu 55 ***
PC: @ 0x5266a0 (unknown) (unknown)
@ 0x7fca1c095520 (unknown) (unknown)
@ 0x7fc8a36b1b40 (unknown) (unknown)
@ 0x95e040 (unknown) (unknown)
[2024-08-20 20:23:48,285 E 118260 118260] logging.cc:365: *** SIGSEGV received at time=1724185428 on cpu 55 ***
[2024-08-20 20:23:48,288 E 118260 118260] logging.cc:365: PC: @ 0x5266a0 (unknown) (unknown)
[2024-08-20 20:23:48,288 E 118260 118260] logging.cc:365: @ 0x7fca1c095520 (unknown) (unknown)
[2024-08-20 20:23:48,292 E 118260 118260] logging.cc:365: @ 0x7fc8a36b1b40 (unknown) (unknown)
[2024-08-20 20:23:48,298 E 118260 118260] logging.cc:365: @ 0x95e040 (unknown) (unknown)
Fatal Python error: Segmentation fault
Stack (most recent call first):
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/triton/compiler/code_generator.py", line 1234 in ast_to_ttir
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/triton/compiler/compiler.py", line 117 in make_ir
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/triton/compiler/compiler.py", line 191 in compile
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/triton/runtime/jit.py", line 416 in run
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/triton/runtime/jit.py", line 167 in <lambda>
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/model_executor/layers/fused_moe/fused_moe.py", line 246 in invoke_fused_moe_kernel
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/model_executor/layers/fused_moe/fused_moe.py", line 513 in fused_experts
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/model_executor/layers/fused_moe/fused_moe.py", line 613 in fused_moe
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/model_executor/layers/fused_moe/layer.py", line 74 in apply
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/model_executor/layers/fused_moe/layer.py", line 209 in forward
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1541 in _call_impl
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1532 in _wrapped_call_impl
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/model_executor/models/mixtral.py", line 96 in forward
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1541 in _call_impl
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1532 in _wrapped_call_impl
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/model_executor/models/mixtral.py", line 233 in forward
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1541 in _call_impl
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1532 in _wrapped_call_impl
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/model_executor/models/mixtral.py", line 277 in forward
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1541 in _call_impl
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1532 in _wrapped_call_impl
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/model_executor/models/mixtral.py", line 349 in forward
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1541 in _call_impl
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1532 in _wrapped_call_impl
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/worker/model_runner.py", line 1341 in execute_model
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115 in decorate_context
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/worker/model_runner.py", line 923 in profile_run
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115 in decorate_context
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/worker/worker.py", line 179 in determine_num_available_blocks
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115 in decorate_context
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/worker/worker_base.py", line 332 in execute_method
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/executor/ray_gpu_executor.py", line 310 in _run_workers
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/executor/distributed_gpu_executor.py", line 38 in determine_num_available_blocks
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/engine/llm_engine.py", line 362 in _initialize_kv_caches
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/engine/llm_engine.py", line 263 in __init__
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/engine/async_llm_engine.py", line 520 in _init_engine
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/engine/async_llm_engine.py", line 373 in __init__
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/engine/async_llm_engine.py", line 444 in from_engine_args
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/entrypoints/openai/api_server.py", line 224 in run_server
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/scripts.py", line 28 in serve
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/lib/python3.11/site-packages/vllm/scripts.py", line 148 in main
File "/local_disk0/.ephemeral_nfs/envs/pythonEnv-295657cb-2b00-4279-ab0b-937f60f2f532/bin/vllm", line 8 in <module>
Extension modules: numpy.core._multiarray_umath, numpy.core._multiarray_tests, numpy.linalg._umath_linalg, numpy.fft._pocketfft_internal, numpy.random._common, numpy.random.bit_generator, numpy.random._bounded_integers, numpy.random._mt19937, numpy.random.mtrand, numpy.random._philox, numpy.random._pcg64, numpy.random._sfc64, numpy.random._generator, torch._C, torch._C._fft, torch._C._linalg, torch._C._nested, torch._C._nn, torch._C._sparse, torch._C._special, _brotli, simplejson._speedups, yaml._yaml, psutil._psutil_linux, psutil._psutil_posix, sentencepiece._sentencepiece, msgpack._cmsgpack, google._upb._message, setproctitle, uvloop.loop, ray._raylet, pvectorc, ujson, regex._regex, scipy._lib._ccallback_c, numba.core.typeconv._typeconv, numba._helperlib, numba._dynfunc, numba._dispatcher, numba.core.runtime._nrt_python, numba.np.ufunc._internal, numba.experimental.jitclass._box, snappy._snappy, lz4._version, lz4.frame._frame, pandas._libs.tslibs.np_datetime, pandas._libs.tslibs.dtypes, pandas._libs.tslibs.base, pandas._libs.tslibs.nattype, pandas._libs.tslibs.timezones, pandas._libs.tslibs.tzconversion, pandas._libs.tslibs.ccalendar, pandas._libs.tslibs.fields, pandas._libs.tslibs.timedeltas, pandas._libs.tslibs.timestamps, pandas._libs.properties, pandas._libs.tslibs.offsets, pandas._libs.tslibs.parsing, pandas._libs.tslibs.conversion, pandas._libs.tslibs.period, pandas._libs.tslibs.vectorized, pandas._libs.ops_dispatch, pandas._libs.missing, pandas._libs.hashtable, pandas._libs.algos, pandas._libs.interval, pandas._libs.tslib, pandas._libs.lib, pandas._libs.hashing, pyarrow.lib, pyarrow._hdfsio, pandas._libs.ops, pyarrow._compute, pandas._libs.arrays, pandas._libs.index, pandas._libs.join, pandas._libs.sparse, pandas._libs.reduction, pandas._libs.indexing, pandas._libs.internals, pandas._libs.writers, pandas._libs.window.aggregations, pandas._libs.window.indexers, pandas._libs.reshape, pandas._libs.tslibs.strptime, pandas._libs.groupby, pandas._libs.testing, pandas._libs.parsers, pandas._libs.json, _cffi_backend, pyarrow._parquet, pyarrow._fs, pyarrow._hdfs, pyarrow._gcsfs, pyarrow._s3fs, multidict._multidict, yarl._quoting_c, aiohttp._helpers, aiohttp._http_writer, aiohttp._http_parser, aiohttp._websocket, frozenlist._frozenlist, xxhash._xxhash, pyarrow._json, markupsafe._speedups, PIL._imaging, grpc._cython.cygrpc, zmq.libzmq, zmq.backend.cython.context, zmq.backend.cython.message, zmq.backend.cython.socket, zmq.backend.cython._device, zmq.backend.cython._poll, zmq.backend.cython._proxy_steerable, zmq.backend.cython._version, zmq.backend.cython.error, zmq.backend.cython.utils, cuda_utils (total: 118)
/usr/lib/python3.11/multiprocessing/resource_tracker.py:224: UserWarning: resource_tracker: There appear to be 1 leaked shared_memory objects to clean up at shutdown
warnings.warn('resource_tracker: There appear to be %d '
9
Mixtral or any mixture of experts model fails due to a error with the fused_moe triton kernel. I think its an issue with an nvidia driver but i cant easily update the driver on databricks.
downgrading to 0.2.7 works since the fused moe is not there, but models like deepseek dont work since they dont have a non fused implementation.
Before submitting a new issue…
- Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.
About this issue
- Original URL
- State: closed
- Created 2 years ago
- Comments: 23
Can you send me a note to rshaw[at]neuralmagic[dot]com
@robertgshaw2-neuralmagic Actually I just set it to run now, will get updated logs with 30mins
I am looking into your issue