Bump vllm from 0.6.3.post1 to 0.7.2 in /examples/speed-benchmark

[dependabot]

Bumps vllm from 0.6.3.post1 to 0.7.2.

Release notes

Sourced from vllm's releases.

v0.7.2

Highlights

• Qwen2.5-VL is now supported in vLLM. Please note that it requires a source installation from Hugging Face transformers library at the moment (#12604)
• Add transformers backend support via --model-impl=transformers. This allows vLLM to be ran with arbitrary Hugging Face text models (#11330, #12785, #12727).
• Performance enhancement to DeepSeek models.
  • Align KV caches entries to start 256 byte boundaries, yielding 43% throughput enhancement (#12676)
  • Apply torch.compile to fused_moe/grouped_topk, yielding 5% throughput enhancement (#12637)
  • Enable MLA for DeepSeek VL2 (#12729)
  • Enable DeepSeek model on ROCm (#12662)

Core Engine

• Use VLLM_LOGITS_PROCESSOR_THREADS to speed up structured decoding in high batch size scenarios (#12368)

Security Update

• Improve hash collision avoidance in prefix caching (#12621)
• Add SPDX-License-Identifier headers to python source files (#12628)

Other

• Enable FusedSDPA support for Intel Gaudi (HPU) (#12359)

What's Changed

• Apply torch.compile to fused_moe/grouped_topk by @​mgoin in vllm-project/vllm#12637
• doc: fixing minor typo in readme.md by @​vicenteherrera in vllm-project/vllm#12643
• [Bugfix] fix moe_wna16 get_quant_method by @​jinzhen-lin in vllm-project/vllm#12648
• [Core] Silence unnecessary deprecation warnings by @​russellb in vllm-project/vllm#12620
• [V1][Minor] Avoid frequently creating ConstantList by @​WoosukKwon in vllm-project/vllm#12653
• [Core][v1] Unify allocating slots in prefill and decode in KV cache manager by @​ShawnD200 in vllm-project/vllm#12608
• [Hardware][Intel GPU] add XPU bf16 support by @​jikunshang in vllm-project/vllm#12392
• [Misc] Add SPDX-License-Identifier headers to python source files by @​russellb in vllm-project/vllm#12628
• [doc][misc] clarify VLLM_HOST_IP for multi-node inference by @​youkaichao in vllm-project/vllm#12667
• [Doc] Deprecate Discord by @​zhuohan123 in vllm-project/vllm#12668
• [Kernel] port sgl moe_align_block_size kernels by @​chenyang78 in vllm-project/vllm#12574
• make sure mistral_common not imported for non-mistral models by @​youkaichao in vllm-project/vllm#12669
• Properly check if all fused layers are in the list of targets by @​eldarkurtic in vllm-project/vllm#12666
• Fix for attention layers to remain unquantized during moe_wn16 quant by @​srikanthsrnvs in vllm-project/vllm#12570
• [cuda] manually import the correct pynvml module by @​youkaichao in vllm-project/vllm#12679
• [ci/build] fix gh200 test by @​youkaichao in vllm-project/vllm#12681
• [Model]: Add transformers backend support by @​ArthurZucker in vllm-project/vllm#11330
• [Misc] Fix improper placement of SPDX header in scripts by @​russellb in vllm-project/vllm#12694
• [Bugfix][Kernel] Fix per-token/per-channel quantization for Hopper scaled mm by @​tlrmchlsmth in vllm-project/vllm#12696
• Squelch MLA warning for Compressed-Tensors Models by @​kylesayrs in vllm-project/vllm#12704
• [Model] Add Deepseek V3 fp8_w8a8 configs for B200 by @​kushanam in vllm-project/vllm#12707
• [MISC] Remove model input dumping when exception by @​comaniac in vllm-project/vllm#12582
• [V1] Revert uncache_blocks and support recaching full blocks by @​comaniac in vllm-project/vllm#12415
• [Core] Improve hash collision avoidance in prefix caching by @​russellb in vllm-project/vllm#12621
• Support Pixtral-Large HF by using llava multimodal_projector_bias config by @​mgoin in vllm-project/vllm#12710
• [Doc] Replace ibm-fms with ibm-ai-platform by @​tdoublep in vllm-project/vllm#12709
• [Quant] Fix use_mla TypeError and support loading pure-sparsity Compressed Tensors configs by @​kylesayrs in vllm-project/vllm#12711
• [AMD][ROCm] Enable DeepSeek model on ROCm by @​hongxiayang in vllm-project/vllm#12662

... (truncated)

Commits

• 0408efc [Misc] Improve error message for incorrect pynvml (#12809)
• 449d1bc [Misc] Remove duplicated DeepSeek V2/V3 model definition (#12793)
• 1a6fcad Improve TransformersModel UX (#12785)
• 56534cd [Bugfix] Fix the test_ultravox.py's license (#12806)
• d88506d [Model] LoRA Support for Ultravox model (#11253)
• 9cdea30 [Misc][Easy] Remove the space from the file name
• 76abd0c [Bugfix] Better FP8 supported defaults
• 5b19b93 [ROCm][Kernel] Using the correct warp_size value
• 75404d0 [VLM] Update compatibility with transformers 4.49
• bf3b79e [VLM] Qwen2.5-VL
• 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 <dependency name> 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)
  You can disable automated security fix PRs for this repo from the Security Alerts page.