[Usage]: Is it possible to use meta-llama/Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8 with vLLM?

[mrakgr]

Your current environment

PyTorch version: 2.5.1+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.5 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: 3.10.16 (main, Dec 11 2024, 16:24:50) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.15.0-125-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.6.77
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: 
GPU 0: NVIDIA H100 80GB HBM3
GPU 1: NVIDIA H100 80GB HBM3
GPU 2: NVIDIA H100 80GB HBM3
GPU 3: NVIDIA H100 80GB HBM3
GPU 4: NVIDIA H100 80GB HBM3
GPU 5: NVIDIA H100 80GB HBM3
GPU 6: NVIDIA H100 80GB HBM3
GPU 7: NVIDIA H100 80GB HBM3

Nvidia driver version: 560.35.03
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.5.0
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, 57 bits virtual
Byte Order:                           Little Endian
CPU(s):                               192
On-line CPU(s) list:                  0-191
Vendor ID:                            GenuineIntel
Model name:                           INTEL(R) XEON(R) PLATINUM 8558
CPU family:                           6
Model:                                207
Thread(s) per core:                   2
Core(s) per socket:                   48
Socket(s):                            2
Stepping:                             2
Frequency boost:                      enabled
CPU max MHz:                          2101.0000
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 tsc_known_freq 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 cat_l2 cdp_l3 invpcid_single intel_ppin cdp_l2 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 rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization:                       VT-x
L1d cache:                            4.5 MiB (96 instances)
L1i cache:                            3 MiB (96 instances)
L2 cache:                             192 MiB (96 instances)
L3 cache:                             520 MiB (2 instances)
NUMA node(s):                         4
NUMA node0 CPU(s):                    0-23,96-119
NUMA node1 CPU(s):                    24-47,120-143
NUMA node2 CPU(s):                    48-71,144-167
NUMA node3 CPU(s):                    72-95,168-191
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:   Not affected
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 / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected

Versions of relevant libraries:
[pip3] numpy==1.26.4
[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-ml-py==12.560.30
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3] pyzmq==26.2.0
[pip3] torch==2.5.1
[pip3] torchvision==0.20.1
[pip3] transformers==4.47.1
[pip3] triton==3.1.0
[conda] numpy                     1.26.4                   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-ml-py              12.560.30                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                     26.2.0                   pypi_0    pypi
[conda] torch                     2.5.1                    pypi_0    pypi
[conda] torchvision               0.20.1                   pypi_0    pypi
[conda] transformers              4.47.1                   pypi_0    pypi
[conda] triton                    3.1.0                    pypi_0    pypi
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.6.6.post1
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0    GPU1    GPU2    GPU3    GPU4    GPU5    GPU6    GPU7    NIC0    NIC1    NIC2    NIC3    NIC4    NIC5    NIC6    NIC7    CPU Affinity    NUMA Affinity GPU NUMA ID
GPU0     X      NV18    NV18    NV18    NV18    NV18    NV18    NV18    PIX     NODE    NODE    SYS     SYS     SYS     SYS     SYS     0-23,96-119  0N/A
GPU1    NV18     X      NV18    NV18    NV18    NV18    NV18    NV18    NODE    PIX     NODE    SYS     SYS     SYS     SYS     SYS     0-23,96-119  0N/A
GPU2    NV18    NV18     X      NV18    NV18    NV18    NV18    NV18    NODE    NODE    PIX     SYS     SYS     SYS     SYS     SYS     0-23,96-119  0N/A
GPU3    NV18    NV18    NV18     X      NV18    NV18    NV18    NV18    SYS     SYS     SYS     PIX     SYS     SYS     SYS     SYS     24-47,120-1431N/A
GPU4    NV18    NV18    NV18    NV18     X      NV18    NV18    NV18    SYS     SYS     SYS     SYS     PIX     NODE    NODE    SYS     48-71,144-1672N/A
GPU5    NV18    NV18    NV18    NV18    NV18     X      NV18    NV18    SYS     SYS     SYS     SYS     NODE    PIX     NODE    SYS     48-71,144-1672N/A
GPU6    NV18    NV18    NV18    NV18    NV18    NV18     X      NV18    SYS     SYS     SYS     SYS     NODE    NODE    PIX     SYS     48-71,144-1672N/A
GPU7    NV18    NV18    NV18    NV18    NV18    NV18    NV18     X      SYS     SYS     SYS     SYS     SYS     SYS     SYS     PIX     72-95,168-1913N/A
NIC0    PIX     NODE    NODE    SYS     SYS     SYS     SYS     SYS      X      NODE    NODE    SYS     SYS     SYS     SYS     SYS
NIC1    NODE    PIX     NODE    SYS     SYS     SYS     SYS     SYS     NODE     X      NODE    SYS     SYS     SYS     SYS     SYS
NIC2    NODE    NODE    PIX     SYS     SYS     SYS     SYS     SYS     NODE    NODE     X      SYS     SYS     SYS     SYS     SYS
NIC3    SYS     SYS     SYS     PIX     SYS     SYS     SYS     SYS     SYS     SYS     SYS      X      SYS     SYS     SYS     SYS
NIC4    SYS     SYS     SYS     SYS     PIX     NODE    NODE    SYS     SYS     SYS     SYS     SYS      X      NODE    NODE    SYS
NIC5    SYS     SYS     SYS     SYS     NODE    PIX     NODE    SYS     SYS     SYS     SYS     SYS     NODE     X      NODE    SYS
NIC6    SYS     SYS     SYS     SYS     NODE    NODE    PIX     SYS     SYS     SYS     SYS     SYS     NODE    NODE     X      SYS
NIC7    SYS     SYS     SYS     SYS     SYS     SYS     SYS     PIX     SYS     SYS     SYS     SYS     SYS     SYS     SYS      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
  NIC2: mlx5_2
  NIC3: mlx5_3
  NIC4: mlx5_4
  NIC5: mlx5_5
  NIC6: mlx5_6
  NIC7: mlx5_7

NVIDIA_VISIBLE_DEVICES=all
CUBLAS_VERSION=12.6.3.3
NVIDIA_REQUIRE_CUDA=cuda>=9.0
CUDA_CACHE_DISABLE=1
NCCL_VERSION=2.22.3
NVIDIA_DRIVER_CAPABILITIES=compute,utility,video
NVIDIA_PRODUCT_NAME=CUDA
CUDA_VERSION=12.6.2.004
CUDNN_FRONTEND_VERSION=1.7.0
CUDNN_VERSION=9.5.0.50
LD_LIBRARY_PATH=/root/miniconda3/envs/vllm/lib/python3.10/site-packages/cv2/../../lib64:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
NVIDIA_BUILD_ID=114391310
CUDA_DRIVER_VERSION=560.35.03
NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS=
CUDA_MODULE_LOADING=LAZY

How would you like to use vllm

I want to run inference of meta-llama/Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8 so I can use it as a draft model in speculative decoding for larger models, but I don't know how to integrate it with vLLM and I suspect it's due to vLLM not supporting the quantization scheme. I get the following errors when I try to run it directly. Is there a setting I could set to make it work or is it completely unsupported at the moment?

(vllm) root@ceti16:~# vllm serve meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8 --host 0.0.0.0 --served-model-name meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8 --port 23331 --gpu-memory-utilization 0.99 --tensor-parallel-size 1 --pipeline-parallel-size 1 --compilation-config 3
INFO 01-24 15:47:34 api_server.py:712] vLLM API server version 0.6.6.post1
INFO 01-24 15:47:34 api_server.py:713] args: Namespace(subparser='serve', model_tag='meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8', config='', host='0.0.0.0', port=23331, 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, chat_template_content_format='auto', response_role='assistant', ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, 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='meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8', task='auto', tokenizer=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, download_dir=None, load_format='auto', config_format=<ConfigFormat.AUTO: 'auto'>, dtype='auto', kv_cache_dtype='auto', quantization_param_path=None, max_model_len=None, guided_decoding_backend='xgrammar', logits_processor_pattern=None, distributed_executor_backend=None, worker_use_ray=False, pipeline_parallel_size=1, tensor_parallel_size=1, max_parallel_loading_workers=None, ray_workers_use_nsight=False, block_size=None, enable_prefix_caching=None, disable_sliding_window=False, use_v2_block_manager=True, num_lookahead_slots=0, seed=0, swap_space=4, cpu_offload_gb=0, gpu_memory_utilization=0.99, num_gpu_blocks_override=None, max_num_batched_tokens=None, max_num_seqs=None, max_logprobs=20, disable_log_stats=False, quantization=None, rope_scaling=None, rope_theta=None, hf_overrides=None, enforce_eager=False, max_seq_len_to_capture=8192, disable_custom_all_reduce=False, 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_model=None, speculative_model_quantization=None, num_speculative_tokens=None, speculative_disable_mqa_scorer=False, 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, disable_logprobs_during_spec_decoding=None, model_loader_extra_config=None, ignore_patterns=[], preemption_mode=None, served_model_name=['meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8'], qlora_adapter_name_or_path=None, otlp_traces_endpoint=None, collect_detailed_traces=None, disable_async_output_proc=False, scheduling_policy='fcfs', override_neuron_config=None, override_pooler_config=None, compilation_config={"level":3,"splitting_ops":["vllm.unified_attention","vllm.unified_attention_with_output"]}, kv_transfer_config=None, worker_cls='auto', generation_config=None, disable_log_requests=False, max_log_len=None, disable_fastapi_docs=False, enable_prompt_tokens_details=False, dispatch_function=<function serve at 0x7f1fe2867a30>)
INFO 01-24 15:47:34 api_server.py:199] Started engine process with PID 638234
INFO 01-24 15:47:35 config.py:2272] Downcasting torch.float32 to torch.float16.
WARNING 01-24 15:47:35 registry.py:406] No model architectures are specified
Traceback (most recent call last):
  File "/root/miniconda3/envs/vllm/bin/vllm", line 8, in <module>
    sys.exit(main())
  File "/root/miniconda3/envs/vllm/lib/python3.10/site-packages/vllm/scripts.py", line 201, in main
    args.dispatch_function(args)
  File "/root/miniconda3/envs/vllm/lib/python3.10/site-packages/vllm/scripts.py", line 42, in serve
    uvloop.run(run_server(args))
  File "/root/miniconda3/envs/vllm/lib/python3.10/site-packages/uvloop/__init__.py", line 82, in run
    return loop.run_until_complete(wrapper())
  File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
  File "/root/miniconda3/envs/vllm/lib/python3.10/site-packages/uvloop/__init__.py", line 61, in wrapper
    return await main
  File "/root/miniconda3/envs/vllm/lib/python3.10/site-packages/vllm/entrypoints/openai/api_server.py", line 740, in run_server
    async with build_async_engine_client(args) as engine_client:
  File "/root/miniconda3/envs/vllm/lib/python3.10/contextlib.py", line 199, in __aenter__
    return await anext(self.gen)
  File "/root/miniconda3/envs/vllm/lib/python3.10/site-packages/vllm/entrypoints/openai/api_server.py", line 118, in build_async_engine_client
    async with build_async_engine_client_from_engine_args(
  File "/root/miniconda3/envs/vllm/lib/python3.10/contextlib.py", line 199, in __aenter__
    return await anext(self.gen)
  File "/root/miniconda3/envs/vllm/lib/python3.10/site-packages/vllm/entrypoints/openai/api_server.py", line 210, in build_async_engine_client_from_engine_args
    engine_config = engine_args.create_engine_config()
  File "/root/miniconda3/envs/vllm/lib/python3.10/site-packages/vllm/engine/arg_utils.py", line 1044, in create_engine_config
    model_config = self.create_model_config()
  File "/root/miniconda3/envs/vllm/lib/python3.10/site-packages/vllm/engine/arg_utils.py", line 970, in create_model_config
    return ModelConfig(
  File "/root/miniconda3/envs/vllm/lib/python3.10/site-packages/vllm/config.py", line 337, in __init__
    self.multimodal_config = self._init_multimodal_config(
  File "/root/miniconda3/envs/vllm/lib/python3.10/site-packages/vllm/config.py", line 392, in _init_multimodal_config
    if ModelRegistry.is_multimodal_model(architectures):
  File "/root/miniconda3/envs/vllm/lib/python3.10/site-packages/vllm/model_executor/models/registry.py", line 461, in is_multimodal_model
    model_cls, _ = self.inspect_model_cls(architectures)
  File "/root/miniconda3/envs/vllm/lib/python3.10/site-packages/vllm/model_executor/models/registry.py", line 416, in inspect_model_cls
    for arch in architectures:
TypeError: 'NoneType' object is not iterable

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.

[mrakgr]

As an aside, if this one cannot be used, could you recommend any alternatives? I've just noticed that on HF you have some quantized Llama models that I could substitute it with. For example:

https://huggingface.co/neuralmagic/Llama-3.2-1B-Instruct-FP8-dynamic
https://huggingface.co/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8
https://huggingface.co/neuralmagic/Llama-3.2-1B-Instruct-FP8

Which one would you recommend I use instead?