vllm
vllm copied to clipboard
Published
20 hours ago •
vllm-project
vllm-project
[Bug]: Loading bnb-community/Llama-4-Scout-17B-16E-Instruct-bnb-4bit error `FusedMoE` quant_method is None
Your current environment
The output of `python collect_env.py`
PyTorch version: 2.6.0+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
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: Could not collect
Libc version: glibc-2.35
Python version: 3.11.11 (main, Dec 11 2024, 16:28:39) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-6.5.0-35-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.2.140
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA A100-SXM4-80GB
Nvidia driver version: 535.183.01
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: 46 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 88
On-line CPU(s) list: 0-87
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) CPU E5-2699 v4 @ 2.20GHz
CPU family: 6
Model: 79
Thread(s) per core: 2
Core(s) per socket: 22
Socket(s): 2
Stepping: 1
CPU max MHz: 3600,0000
CPU min MHz: 1200,0000
BogoMIPS: 4399.99
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 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 pti ssbd ibrs ibpb stibp tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm rdt_a rdseed adx smap intel_pt xsaveopt cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts vnmi md_clear flush_l1d
Virtualization: VT-x
L1d cache: 1,4 MiB (44 instances)
L1i cache: 1,4 MiB (44 instances)
L2 cache: 11 MiB (44 instances)
L3 cache: 110 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86
NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: KVM: Mitigation: VMX disabled
Vulnerability L1tf: Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable
Vulnerability Mds: Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Meltdown: Mitigation; PTI
Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Retpolines; IBPB conditional; IBRS_FW; STIBP conditional; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT vulnerable
Versions of relevant libraries:
[pip3] numpy==2.2.4
[pip3] nvidia-cublas-cu12==12.4.5.8
[pip3] nvidia-cuda-cupti-cu12==12.4.127
[pip3] nvidia-cuda-nvrtc-cu12==12.4.127
[pip3] nvidia-cuda-runtime-cu12==12.4.127
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.2.1.3
[pip3] nvidia-curand-cu12==10.3.5.147
[pip3] nvidia-cusolver-cu12==11.6.1.9
[pip3] nvidia-cusparse-cu12==12.3.1.170
[pip3] nvidia-cusparselt-cu12==0.6.2
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3] pyzmq==26.4.0
[pip3] torch==2.6.0
[pip3] torchaudio==2.6.0
[pip3] torchvision==0.21.0
[pip3] transformers==4.51.3
[pip3] triton==3.2.0
[conda] numpy 2.2.4 pypi_0 pypi
[conda] nvidia-cublas-cu12 12.4.5.8 pypi_0 pypi
[conda] nvidia-cuda-cupti-cu12 12.4.127 pypi_0 pypi
[conda] nvidia-cuda-nvrtc-cu12 12.4.127 pypi_0 pypi
[conda] nvidia-cuda-runtime-cu12 12.4.127 pypi_0 pypi
[conda] nvidia-cudnn-cu12 9.1.0.70 pypi_0 pypi
[conda] nvidia-cufft-cu12 11.2.1.3 pypi_0 pypi
[conda] nvidia-curand-cu12 10.3.5.147 pypi_0 pypi
[conda] nvidia-cusolver-cu12 11.6.1.9 pypi_0 pypi
[conda] nvidia-cusparse-cu12 12.3.1.170 pypi_0 pypi
[conda] nvidia-cusparselt-cu12 0.6.2 pypi_0 pypi
[conda] nvidia-nccl-cu12 2.21.5 pypi_0 pypi
[conda] nvidia-nvjitlink-cu12 12.4.127 pypi_0 pypi
[conda] nvidia-nvtx-cu12 12.4.127 pypi_0 pypi
[conda] pyzmq 26.4.0 pypi_0 pypi
[conda] torch 2.6.0 pypi_0 pypi
[conda] torchaudio 2.6.0 pypi_0 pypi
[conda] torchvision 0.21.0 pypi_0 pypi
[conda] transformers 4.51.3 pypi_0 pypi
[conda] triton 3.2.0 pypi_0 pypi
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.8.4
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 NIC0 NIC1 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X PHB PHB 1,3,5,7,9,11 1 N/A
NIC0 PHB X PIX
NIC1 PHB PIX X
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
NIC Legend:
NIC0: mlx5_0
NIC1: mlx5_1
LD_LIBRARY_PATH=/usr/local/cuda-12.2/lib64
NCCL_CUMEM_ENABLE=0
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY
🐛 Describe the bug
I'm trying to load this model: bnb-community/Llama-4-Scout-17B-16E-Instruct-bnb-4bit
The model is quantized model of llama 4 scout in 4 bit quantized using bitsandbytes.
Here is how I run the model:
vllm serve models/llama4-17Bx16E-Instruct-bnb-4bit --host 0.0.0.0 --port 8000 --max-model-len 8192 --load-format bitsandbytes --quantization bitsandbytes --override-generation-config='{"attn_temperature_tuning": true}'
But, I got this error:
INFO 04-16 16:34:25 [__init__.py:239] Automatically detected platform cuda.
INFO 04-16 16:34:27 [api_server.py:1034] vLLM API server version 0.8.4
INFO 04-16 16:34:27 [api_server.py:1035] args: Namespace(subparser='serve', model_tag='models/llama4-17Bx16E-Instruct-bnb-4bit', config='', host='0.0.0.0', port=8000, uvicorn_log_level='info', disable_uvicorn_access_log=False, allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key=None, lora_modules=None, prompt_adapters=None, chat_template=None, chat_template_content_format='auto', response_role='assistant', ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, enable_ssl_refresh=False, ssl_cert_reqs=0, root_path=None, middleware=[], return_tokens_as_token_ids=False, disable_frontend_multiprocessing=False, enable_request_id_headers=False, enable_auto_tool_choice=False, tool_call_parser=None, tool_parser_plugin='', model='models/llama4-17Bx16E-Instruct-bnb-4bit', task='auto', tokenizer=None, hf_config_path=None, skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='auto', trust_remote_code=False, allowed_local_media_path=None, load_format='bitsandbytes', download_dir=None, model_loader_extra_config=None, use_tqdm_on_load=True, config_format=<ConfigFormat.AUTO: 'auto'>, dtype='auto', kv_cache_dtype='auto', max_model_len=8192, guided_decoding_backend='auto', logits_processor_pattern=None, model_impl='auto', distributed_executor_backend=None, pipeline_parallel_size=1, tensor_parallel_size=1, data_parallel_size=1, enable_expert_parallel=False, max_parallel_loading_workers=None, ray_workers_use_nsight=False, disable_custom_all_reduce=False, block_size=None, enable_prefix_caching=None, prefix_caching_hash_algo='builtin', disable_sliding_window=False, use_v2_block_manager=True, num_lookahead_slots=0, seed=None, swap_space=4, cpu_offload_gb=0, gpu_memory_utilization=0.9, num_gpu_blocks_override=None, max_num_batched_tokens=None, max_num_partial_prefills=1, max_long_partial_prefills=1, long_prefill_token_threshold=0, max_num_seqs=None, max_logprobs=20, disable_log_stats=False, quantization='bitsandbytes', rope_scaling=None, rope_theta=None, hf_token=None, hf_overrides=None, enforce_eager=False, max_seq_len_to_capture=8192, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config=None, limit_mm_per_prompt=None, mm_processor_kwargs=None, disable_mm_preprocessor_cache=False, enable_lora=False, enable_lora_bias=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', num_scheduler_steps=1, multi_step_stream_outputs=True, scheduler_delay_factor=0.0, enable_chunked_prefill=None, speculative_config=None, ignore_patterns=[], preemption_mode=None, served_model_name=None, qlora_adapter_name_or_path=None, show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, disable_async_output_proc=False, scheduling_policy='fcfs', scheduler_cls='vllm.core.scheduler.Scheduler', override_neuron_config=None, override_pooler_config=None, compilation_config=None, kv_transfer_config=None, worker_cls='auto', worker_extension_cls='', generation_config='auto', override_generation_config={'attn_temperature_tuning': True}, enable_sleep_mode=False, calculate_kv_scales=False, additional_config=None, enable_reasoning=False, reasoning_parser=None, disable_cascade_attn=False, disable_chunked_mm_input=False, disable_log_requests=False, max_log_len=None, disable_fastapi_docs=False, enable_prompt_tokens_details=False, enable_server_load_tracking=False, dispatch_function=<function ServeSubcommand.cmd at 0x7089198cc9a0>)
INFO 04-16 16:34:35 [config.py:689] This model supports multiple tasks: {'score', 'reward', 'classify', 'embed', 'generate'}. Defaulting to 'generate'.
WARNING 04-16 16:34:37 [config.py:768] bitsandbytes quantization is not fully optimized yet. The speed can be slower than non-quantized models.
INFO 04-16 16:34:37 [config.py:1901] Chunked prefill is enabled with max_num_batched_tokens=2048.
INFO 04-16 16:34:42 [__init__.py:239] Automatically detected platform cuda.
INFO 04-16 16:34:45 [core.py:61] Initializing a V1 LLM engine (v0.8.4) with config: model='models/llama4-17Bx16E-Instruct-bnb-4bit', speculative_config=None, tokenizer='models/llama4-17Bx16E-Instruct-bnb-4bit', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, override_neuron_config=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=8192, download_dir=None, load_format=LoadFormat.BITSANDBYTES, tensor_parallel_size=1, pipeline_parallel_size=1, disable_custom_all_reduce=False, quantization=bitsandbytes, enforce_eager=False, kv_cache_dtype=auto, device_config=cuda, decoding_config=DecodingConfig(guided_decoding_backend='auto', reasoning_backend=None), observability_config=ObservabilityConfig(show_hidden_metrics=False, otlp_traces_endpoint=None, collect_model_forward_time=False, collect_model_execute_time=False), seed=None, served_model_name=models/llama4-17Bx16E-Instruct-bnb-4bit, num_scheduler_steps=1, multi_step_stream_outputs=True, enable_prefix_caching=True, chunked_prefill_enabled=True, use_async_output_proc=True, disable_mm_preprocessor_cache=False, mm_processor_kwargs=None, pooler_config=None, compilation_config={"level":3,"custom_ops":["none"],"splitting_ops":["vllm.unified_attention","vllm.unified_attention_with_output"],"use_inductor":true,"compile_sizes":[],"use_cudagraph":true,"cudagraph_num_of_warmups":1,"cudagraph_capture_sizes":[512,504,496,488,480,472,464,456,448,440,432,424,416,408,400,392,384,376,368,360,352,344,336,328,320,312,304,296,288,280,272,264,256,248,240,232,224,216,208,200,192,184,176,168,160,152,144,136,128,120,112,104,96,88,80,72,64,56,48,40,32,24,16,8,4,2,1],"max_capture_size":512}
WARNING 04-16 16:34:45 [utils.py:2444] Methods determine_num_available_blocks,device_config,get_cache_block_size_bytes,initialize_cache not implemented in <vllm.v1.worker.gpu_worker.Worker object at 0x74e7efa28b50>
INFO 04-16 16:34:46 [parallel_state.py:959] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, TP rank 0
INFO 04-16 16:34:46 [cuda.py:221] Using Flash Attention backend on V1 engine.
INFO 04-16 16:34:52 [gpu_model_runner.py:1276] Starting to load model models/llama4-17Bx16E-Instruct-bnb-4bit...
INFO 04-16 16:34:53 [config.py:3466] cudagraph sizes specified by model runner [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 264, 272, 280, 288, 296, 304, 312, 320, 328, 336, 344, 352, 360, 368, 376, 384, 392, 400, 408, 416, 424, 432, 440, 448, 456, 464, 472, 480, 488, 496, 504, 512] is overridden by config [512, 384, 256, 128, 4, 2, 1, 392, 264, 136, 8, 400, 272, 144, 16, 408, 280, 152, 24, 416, 288, 160, 32, 424, 296, 168, 40, 432, 304, 176, 48, 440, 312, 184, 56, 448, 320, 192, 64, 456, 328, 200, 72, 464, 336, 208, 80, 472, 344, 216, 88, 120, 480, 352, 248, 224, 96, 488, 504, 360, 232, 104, 496, 368, 240, 112, 376]
HERE IS THE QUANT CONFIG BitsAndBytesConfig(load_in_8bit=False, load_in_4bit=True, bnb_4bit_compute_dtype=bfloat16, bnb_4bit_quant_storage=uint8, bnb_4bit_quant_type=nf4, llm_int8_skip_modules=[])
ERROR 04-16 16:34:54 [core.py:387] EngineCore hit an exception: Traceback (most recent call last):
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/v1/engine/core.py", line 378, in run_engine_core
ERROR 04-16 16:34:54 [core.py:387] engine_core = EngineCoreProc(*args, **kwargs)
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/v1/engine/core.py", line 320, in __init__
ERROR 04-16 16:34:54 [core.py:387] super().__init__(vllm_config, executor_class, log_stats)
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/v1/engine/core.py", line 67, in __init__
ERROR 04-16 16:34:54 [core.py:387] self.model_executor = executor_class(vllm_config)
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/executor/executor_base.py", line 52, in __init__
ERROR 04-16 16:34:54 [core.py:387] self._init_executor()
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/executor/uniproc_executor.py", line 47, in _init_executor
ERROR 04-16 16:34:54 [core.py:387] self.collective_rpc("load_model")
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/executor/uniproc_executor.py", line 56, in collective_rpc
ERROR 04-16 16:34:54 [core.py:387] answer = run_method(self.driver_worker, method, args, kwargs)
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/utils.py", line 2378, in run_method
ERROR 04-16 16:34:54 [core.py:387] return func(*args, **kwargs)
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^^^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/v1/worker/gpu_worker.py", line 136, in load_model
ERROR 04-16 16:34:54 [core.py:387] self.model_runner.load_model()
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/v1/worker/gpu_model_runner.py", line 1279, in load_model
ERROR 04-16 16:34:54 [core.py:387] self.model = get_model(vllm_config=self.vllm_config)
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/model_loader/__init__.py", line 14, in get_model
ERROR 04-16 16:34:54 [core.py:387] return loader.load_model(vllm_config=vllm_config)
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/model_loader/loader.py", line 1289, in load_model
ERROR 04-16 16:34:54 [core.py:387] model = _initialize_model(vllm_config=vllm_config)
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/model_loader/loader.py", line 133, in _initialize_model
ERROR 04-16 16:34:54 [core.py:387] return model_class(vllm_config=vllm_config, prefix=prefix)
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/mllama4.py", line 676, in __init__
ERROR 04-16 16:34:54 [core.py:387] self.language_model = _initialize_model(
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/model_loader/loader.py", line 133, in _initialize_model
ERROR 04-16 16:34:54 [core.py:387] return model_class(vllm_config=vllm_config, prefix=prefix)
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/llama4.py", line 480, in __init__
ERROR 04-16 16:34:54 [core.py:387] super().__init__(vllm_config=vllm_config,
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/llama.py", line 486, in __init__
ERROR 04-16 16:34:54 [core.py:387] self.model = self._init_model(vllm_config=vllm_config,
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/llama4.py", line 488, in _init_model
ERROR 04-16 16:34:54 [core.py:387] return Llama4Model(vllm_config=vllm_config,
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/compilation/decorators.py", line 151, in __init__
ERROR 04-16 16:34:54 [core.py:387] old_init(self, vllm_config=vllm_config, prefix=prefix, **kwargs)
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/llama4.py", line 330, in __init__
ERROR 04-16 16:34:54 [core.py:387] super().__init__(vllm_config=vllm_config,
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/compilation/decorators.py", line 151, in __init__
ERROR 04-16 16:34:54 [core.py:387] old_init(self, vllm_config=vllm_config, prefix=prefix, **kwargs)
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/llama.py", line 321, in __init__
ERROR 04-16 16:34:54 [core.py:387] self.start_layer, self.end_layer, self.layers = make_layers(
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/utils.py", line 609, in make_layers
ERROR 04-16 16:34:54 [core.py:387] [PPMissingLayer() for _ in range(start_layer)] + [
ERROR 04-16 16:34:54 [core.py:387] ^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/utils.py", line 610, in <listcomp>
ERROR 04-16 16:34:54 [core.py:387] maybe_offload_to_cpu(layer_fn(prefix=f"{prefix}.{idx}"))
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/llama.py", line 323, in <lambda>
ERROR 04-16 16:34:54 [core.py:387] lambda prefix: layer_type(config=config,
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/llama4.py", line 279, in __init__
ERROR 04-16 16:34:54 [core.py:387] self.feed_forward = Llama4MoE(
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/llama4.py", line 73, in __init__
ERROR 04-16 16:34:54 [core.py:387] self.experts = FusedMoE(
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] File "/home/fahadh/anaconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/layers/fused_moe/layer.py", line 503, in __init__
ERROR 04-16 16:34:54 [core.py:387] assert self.quant_method is not None
ERROR 04-16 16:34:54 [core.py:387] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 04-16 16:34:54 [core.py:387] AssertionError
ERROR 04-16 16:34:54 [core.py:387]
CRITICAL 04-16 16:34:54 [core_client.py:359] Got fatal signal from worker processes, shutting down. See stack trace above for root cause issue.
Killed
Seems like when getting quant_method using quant_config.get_quant_method(self, prefix), because bitsandbytes only accept instance of LinearBase and FusedMoE is not subclass of it, the quant_method is returned None and the error is shown.
Is there any simple patch to fix this or maybe there is already pull request fixing this?
Before submitting a new issue...
- [x] 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.
Please ref to this ticket here: #16121. bitsandbytes doesn't support
FusedMoEnow.
Ah, okay. So that means I have to wait llmcompressor to support llama4 model.
Here is an officially supported INT4 Llama-4 checkpoint for vllm: https://huggingface.co/RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16 (Make sure to use the nightly vllm)
