Bump vllm from 0.5.4 to 0.5.5 in /docker

[dependabot[bot]]

Bumps vllm from 0.5.4 to 0.5.5.

Release notes

Sourced from vllm's releases.

v0.5.5

Highlights

Performance Update

• We introduced a new mode that schedule multiple GPU steps in advance, reducing CPU overhead (#7000, #7387, #7452, #7703). Initial result shows 20% improvements in QPS for a single GPU running 8B and 30B models. You can set --num-scheduler-steps 8 as a parameter to the API server (via vllm serve) or AsyncLLMEngine. We are working on expanding the coverage to LLM class and aiming to turning it on by default
• Various enhancements:
  • Use flashinfer sampling kernel when avaiable, leading to 7% decoding throughput speedup (#7137)
  • Reduce Python allocations, leading to 24% throughput speedup (#7162, 7364)
  • Improvements to the zeromq based decoupled frontend (#7570, #7716, #7484)

Model Support

• Support Jamba 1.5 (#7415, #7601, #6739)
• Support for the first audio model UltravoxModel (#7615, #7446)
• Improvements to vision models:
  • Support image embeddings as input (#6613)
  • Support SigLIP encoder and alternative decoders for LLaVA models (#7153)
• Support loading GGUF model (#5191) with tensor parallelism (#7520)
• Progress in encoder decoder models: support for serving encoder/decoder models (#7258), and architecture for cross-attention (#4942)

Hardware Support

• AMD: Add fp8 Linear Layer for rocm (#7210)
• Enhancements to TPU support: load time W8A16 quantization (#7005), optimized rope (#7635), and support multi-host inference (#7457).
• Intel: various refactoring for worker, executor, and model runner (#7686, #7712)

Others

• Optimize prefix caching performance (#7193)
• Speculative decoding
  • Use target model max length as default for draft model (#7706)
  • EAGLE Implementation with Top-1 proposer (#6830)
• Entrypoints
  • A new chat method in the LLM class (#5049)
  • Support embeddings in the run_batch API (#7132)
  • Support prompt_logprobs in Chat Completion (#7453)
• Quantizations
  • Expand MoE weight loading + Add Fused Marlin MoE Kernel (#7527)
  • Machete - Hopper Optimized Mixed Precision Linear Kernel (#7174)
• torch.compile: register custom ops for kernels (#7591, #7594, #7536)

What's Changed

• [ci][frontend] deduplicate tests by @​youkaichao in vllm-project/vllm#7101
• [Doc] [SpecDecode] Update MLPSpeculator documentation by @​tdoublep in vllm-project/vllm#7100
• [Bugfix] Specify device when loading LoRA and embedding tensors by @​jischein in vllm-project/vllm#7129
• [MISC] Use non-blocking transfer in prepare_input by @​comaniac in vllm-project/vllm#7172
• [Core] Support loading GGUF model by @​Isotr0py in vllm-project/vllm#5191
• [Build] Add initial conditional testing spec by @​simon-mo in vllm-project/vllm#6841
• [LoRA] Relax LoRA condition by @​jeejeelee in vllm-project/vllm#7146
• [Model] Support SigLIP encoder and alternative decoders for LLaVA models by @​DarkLight1337 in vllm-project/vllm#7153
• [BugFix] Fix DeepSeek remote code by @​dsikka in vllm-project/vllm#7178
• [ BugFix ] Fix ZMQ when VLLM_PORT is set by @​robertgshaw2-neuralmagic in vllm-project/vllm#7205
• [Bugfix] add gguf dependency by @​kpapis in vllm-project/vllm#7198

... (truncated)

Commits

• 09c7792 Bump version to v0.5.5 (#7823)
• f1df5db [Misc] Update marlin to use vLLMParameters (#7803)
• 35ee2ad [github][misc] promote asking llm first (#7809)
• e25fee5 [BugFix] Fix server crash on empty prompt (#7746)
• faeddb5 [misc] Add Torch profiler support for CPU-only devices (#7806)
• fc5ebbd [Hardware][Intel GPU] refactor xpu_model_runner for tp (#7712)
• c01a6cb [Ray backend] Better error when pg topology is bad. (#7584)
• b903e1b [Frontend] error suppression cleanup (#7786)
• a152246 [Misc] fix typo in triton import warning (#7794)
• 666ad0a [ci] Cleanup & refactor Dockerfile to pass different Python versions and scca...
• 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) You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/NVIDIA/RULER/network/alerts).