[Bug]: tensorizer error: name '_write_stream' is not defined

[g-eoj]

Your current environment

Collecting environment information...
PyTorch version: 2.3.1+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

OS: Ubuntu 24.04 LTS (x86_64)
GCC version: (Ubuntu 13.2.0-23ubuntu4) 13.2.0
Clang version: Could not collect
CMake version: version 3.30.1
Libc version: glibc-2.39

Python version: 3.10.14 (main, May  6 2024, 19:42:50) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-6.8.0-1010-aws-x86_64-with-glibc2.39
Is CUDA available: True
CUDA runtime version: 12.0.140
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA A10G
Nvidia driver version: 535.183.01
cuDNN version: Could not collect
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):                               8
On-line CPU(s) list:                  0-7
Vendor ID:                            AuthenticAMD
Model name:                           AMD EPYC 7R32
CPU family:                           23
Model:                                49
Thread(s) per core:                   2
Core(s) per socket:                   4
Socket(s):                            1
Stepping:                             0
BogoMIPS:                             5600.00
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 ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru wbnoinvd arat npt nrip_save rdpid
Hypervisor vendor:                    KVM
Virtualization type:                  full
L1d cache:                            128 KiB (4 instances)
L1i cache:                            128 KiB (4 instances)
L2 cache:                             2 MiB (4 instances)
L3 cache:                             16 MiB (1 instance)
NUMA node(s):                         1
NUMA node0 CPU(s):                    0-7
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:               Mitigation; untrained return thunk; SMT enabled with STIBP protection
Vulnerability Spec rstack overflow:   Vulnerable: Safe RET, no microcode
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; 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] numpy==1.26.4
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] torch==2.3.1
[pip3] torchvision==0.18.1
[pip3] transformers==4.43.2
[pip3] triton==2.3.1
[conda] numpy                     1.26.4                   pypi_0    pypi
[conda] nvidia-nccl-cu12          2.20.5                   pypi_0    pypi
[conda] torch                     2.3.1                    pypi_0    pypi
[conda] torchvision               0.18.1                   pypi_0    pypi
[conda] transformers              4.43.2                   pypi_0    pypi
[conda] triton                    2.3.1                    pypi_0    pypi
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.5.3.post1
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0	CPU Affinity	NUMA Affinity	GPU NUMA ID
GPU0	 X 	0-7	0		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

When following https://docs.vllm.ai/en/stable/getting_started/examples/tensorize_vllm_model.html#, I get an error. I saved the the script to tensorizer.py and ran it with the command:

python tensorize.py --model facebook/opt-125m serialize --serialized-directory models

Output:

INFO 07-25 16:06:22 llm_engine.py:176] Initializing an LLM engine (v0.5.3.post1) with config: model='facebook/opt-125m', speculative_config=None, tokenizer='facebook/opt-125m', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, rope_scaling=None, rope_theta=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.float16, max_seq_len=2048, download_dir=None, load_format=LoadFormat.AUTO, tensor_parallel_size=1, 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=facebook/opt-125m, use_v2_block_manager=False, enable_prefix_caching=False)
INFO 07-25 16:06:27 model_runner.py:680] Starting to load model facebook/opt-125m...
INFO 07-25 16:06:27 weight_utils.py:223] Using model weights format ['*.bin']
Loading pt checkpoint shards:   0% Completed | 0/1 [00:00<?, ?it/s]
Loading pt checkpoint shards: 100% Completed | 1/1 [00:00<00:00,  4.32it/s]
Loading pt checkpoint shards: 100% Completed | 1/1 [00:00<00:00,  4.32it/s]

INFO 07-25 16:06:28 model_runner.py:692] Loading model weights took 0.2389 GB
INFO 07-25 16:06:29 gpu_executor.py:102] # GPU blocks: 34638, # CPU blocks: 7281
INFO 07-25 16:06:35 model_runner.py:980] Capturing the model for CUDA graphs. This may lead to unexpected consequences if the model is not static. To run the model in eager mode, set 'enforce_eager=True' or use '--enforce-eager' in the CLI.
INFO 07-25 16:06:35 model_runner.py:984] CUDA graphs can take additional 1~3 GiB memory per GPU. If you are running out of memory, consider decreasing `gpu_memory_utilization` or enforcing eager mode. You can also reduce the `max_num_seqs` as needed to decrease memory usage.
INFO 07-25 16:06:42 model_runner.py:1181] Graph capturing finished in 8 secs.
[rank0]: Traceback (most recent call last):
[rank0]:   File "/home/ubuntu/tensorize.py", line 228, in <module>
[rank0]:     tensorizer.tensorize_vllm_model(engine_args, tensorizer_config)
[rank0]:   File "/home/ubuntu/miniconda3/envs/vllm/lib/python3.10/site-packages/vllm/model_executor/model_loader/tensorizer.py", line 472, in tensorize_vllm_model
[rank0]:     serialize_vllm_model(
[rank0]:   File "/home/ubuntu/miniconda3/envs/vllm/lib/python3.10/site-packages/vllm/model_executor/model_loader/tensorizer.py", line 429, in serialize_vllm_model
[rank0]:     with _write_stream(output_file, **tensorizer_args.stream_params) as stream:
[rank0]: NameError: name '_write_stream' is not defined

[g-eoj]

The issue is caused by missing tensorizer package. The example and docs have some wrong info. For example the script docstring says:

Install vllm with tensorizer support using `pip install vllm[tensorizer]`.

but pip reports: no matches found: vllm[tensorizer].

[g-eoj]

So this isn't a bug but docs issue. Closing this and will look into making a PR for docs.