chore(deps): bump vllm from 0.4.0 to 0.4.1 in /openllm-python

[dependabot[bot]]

Bumps vllm from 0.4.0 to 0.4.1.

Release notes

Sourced from vllm's releases.

v0.4.1

Highlights

Features

• Support and enhance CommandR+ (#3829), minicpm (#3893), Meta Llama 3 (#4175, #4182), Mixtral 8x22b (#4073, #4002)
• Support private model registration, and updating our support policy (#3871, 3948)
• Support PyTorch 2.2.1 and Triton 2.2.0 (#4061, #4079, #3805, #3904, #4271)
• Add option for using LM Format Enforcer for guided decoding (#3868)
• Add option for optionally initialize tokenizer and detokenizer (#3748)
• Add option for load model using tensorizer (#3476)

Enhancements

• vLLM is now mostly type checked by mypy (#3816, #4006, #4161, #4043)
• Progress towards chunked prefill scheduler (#3550, #3853, #4280, #3884)
• Progress towards speculative decoding (#3250, #3706, #3894)
• Initial support with dynamic per-tensor scaling via FP8 (#4118)

Hardwares

• Intel CPU inference backend is added (#3993, #3634)
• AMD backend is enhanced with Triton kernel and e4m3fn KV cache (#3643, #3290)

What's Changed

• [Kernel] Layernorm performance optimization by @​mawong-amd in vllm-project/vllm#3662
• [Doc] Update installation doc for build from source and explain the dependency on torch/cuda version by @​youkaichao in vllm-project/vllm#3746
• [CI/Build] Make Marlin Tests Green by @​robertgshaw2-neuralmagic in vllm-project/vllm#3753
• [Misc] Minor fixes in requirements.txt by @​WoosukKwon in vllm-project/vllm#3769
• [Misc] Some minor simplifications to detokenization logic by @​njhill in vllm-project/vllm#3670
• [Misc] Fix Benchmark TTFT Calculation for Chat Completions by @​ywang96 in vllm-project/vllm#3768
• [Speculative decoding 4/9] Lookahead scheduling for speculative decoding by @​cadedaniel in vllm-project/vllm#3250
• [Misc] Add support for new autogptq checkpoint_format by @​Qubitium in vllm-project/vllm#3689
• [Misc] [CI/Build] Speed up block manager CPU-only unit tests ~10x by opting-out of GPU cleanup by @​cadedaniel in vllm-project/vllm#3783
• [Hardware][Intel] Add CPU inference backend by @​bigPYJ1151 in vllm-project/vllm#3634
• [HotFix] [CI/Build] Minor fix for CPU backend CI by @​bigPYJ1151 in vllm-project/vllm#3787
• [Frontend][Bugfix] allow using the default middleware with a root path by @​A-Mahla in vllm-project/vllm#3788
• [Doc] Fix vLLMEngine Doc Page by @​ywang96 in vllm-project/vllm#3791
• [CI/Build] fix TORCH_CUDA_ARCH_LIST in wheel build by @​youkaichao in vllm-project/vllm#3801
• Fix crash when try torch.cuda.set_device in worker by @​leiwen83 in vllm-project/vllm#3770
• [Bugfix] Add __init__.py files for vllm/core/block/ and vllm/spec_decode/ by @​mgoin in vllm-project/vllm#3798
• [CI/Build] 0.4.0.post1, fix sm 7.0/7.5 binary by @​youkaichao in vllm-project/vllm#3803
• [Speculative decoding] Adding configuration object for speculative decoding by @​cadedaniel in vllm-project/vllm#3706
• [BugFix] Use different mechanism to get vllm version in is_cpu() by @​njhill in vllm-project/vllm#3804
• [Doc] Update README.md by @​robertgshaw2-neuralmagic in vllm-project/vllm#3806
• [Doc] Update contribution guidelines for better onboarding by @​michaelfeil in vllm-project/vllm#3819
• [3/N] Refactor scheduler for chunked prefill scheduling by @​rkooo567 in vllm-project/vllm#3550
• Enable scaled FP8 (e4m3fn) KV cache on ROCm (AMD GPU) by @​AdrianAbeyta in vllm-project/vllm#3290
• [Misc] Publish 3rd meetup slides by @​WoosukKwon in vllm-project/vllm#3835
• Fixes the argument for local_tokenizer_group by @​sighingnow in vllm-project/vllm#3754
• [Core] Enable hf_transfer by default if available by @​michaelfeil in vllm-project/vllm#3817
• [Bugfix] Add kv_scale input parameter to CPU backend by @​WoosukKwon in vllm-project/vllm#3840
• [Core] [Frontend] Make detokenization optional by @​mgerstgrasser in vllm-project/vllm#3749

... (truncated)

Commits

• 468d761 [Misc] Reduce supported Punica dtypes (#4304)
• e4bf860 [CI][Build] change pynvml to nvidia-ml-py (#4302)
• 91f50a6 [Core][Distributed] use cpu/gloo to initialize pynccl (#4248)
• 79a268c [BUG] fixed fp8 conflict with aqlm (#4307)
• eace8bf [Kernel] FP8 support for MoE kernel / Mixtral (#4244)
• 1e8f425 [Bugfix][Frontend] Raise exception when file-like chat template fails to be o...
• 2b7949c AQLM CUDA support (#3287)
• 62b5166 [CI] Add ccache for wheel builds job (#4281)
• d86285a [Core][Logging] Add last frame information for better debugging (#4278)
• d87f39e [Bugfix] Add init_cached_hf_modules to RayWorkerWrapper (#4286)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[dependabot[bot]]

Superseded by #974.