Release notes from vllm
Articles about Release notes from vllm
V0.32.0rc0: [HiSparse] Report host pool in KV cache capacity logs (#60285)
Signed-off-by: Matthew Bonanni mbonanni@redhat.com Co-authored-by: Claude Opus 5.5 noreply@anthropic.com
Release proto-v0.5.0 · vllm-project/vllm
Release vllm-proto 0.5.0
V0.31.1rc0: [Metrics] Expose cached prompt tokens by cache tier (#56318)
Signed-off-by: Cam Quilici cjquilici@gmail.com Signed-off-by: Cam Quilici cameron@semianalysis.com Co-authored-by: Cam Quilici cameron@semianalysis.com Co-authored-by: Nick Hill nickhill123@gmail.com Co-authored-by: Yifan Qiao yifanqiao@inferact.ai
Release v0.31.0 · vllm-project/vllm
v0.31.0 Highlights This release features 717 commits from 307 contributors (96 new)! DeepSeek-V4.1-Flash performance: FlashMLA mega attention with the V4.1 NVFP4 compressed KV cache is now the SM1
Release v0.31.0rc4 · vllm-project/vllm
[Bugfix][HiSparse] Fix MTP acceptance collapse under FULL graphs with
V0.31.0rc3: [Model Runner V2] Support randomized dummy inputs (#58411)
Signed-off-by: Robert Shaw robshaw@redhat.com Co-authored-by: Robert Shaw robshaw@redhat.com Co-authored-by: Claude Opus 5.5 noreply@anthropic.com Co-authored-by: mergify[bot] Co-authored-by: Nick Hill nickhill123@gmail.com (cherry picked from commit e5e38ba)
Release proto-v0.4.0 · vllm-project/vllm
Release vllm-proto 0.4.0
Release v0.31.0rc2 · vllm-project/vllm
[Bugfix][Mamba] Keep the prompt-end prefill checkpoint under sparse r
V0.31.0rc1: [CI/Build] Skip the snapshot runtime on CUDA 12.x images (#59118)
Signed-off-by: khluu khluu000@gmail.com Co-authored-by: Claude Opus 5.5 noreply@anthropic.com (cherry picked from commit aedaba8)
V0.30.1rc0: [ROCm][CI] Add MI355 dense NVFP4 and MoRI kernel mirrors (#58281)
Signed-off-by: Andreas Karatzas akaratza@amd.com Co-authored-by: OpenAI Codex noreply@openai.com
Release v0.30.0 · vllm-project/vllm
v0.30.0 Highlights This release features 762 commits from 315 contributors (104 new)! New models: DeepSeek-V4.1-Flash (#56214, #56228, #56208) with the whole KV stored in MXFP8 through the FlashML
Release v0.30.0rc2 · vllm-project/vllm
[Bugfix][NIXL] Avoid receive reports for notification-only requests (
V0.30.0rc1: [Bugfix] Isolate supplemental FlashInfer BF16 autotuning (#57285)
Signed-off-by: jiahanc 173873397+jiahanc@users.noreply.github.com Co-authored-by: OpenAI Codex codex@openai.com
Release proto-v0.3.0 · vllm-project/vllm
Release vllm-proto 0.3.0
Proto-v0.2.0: vllm-proto 0.2.0
Validated by PR #56538 CI at fa2a26f.
Release v0.29.1rc0 · vllm-project/vllm
[watermarking] Dual-key gumbel-max watermarking for speculative decod