v0.33.0 Highlights This release features 927 commits from 389 contributors (122 new)! New models: Reflection Beam-1.0 (501B MoE, 23B active) with its DFlash2 drafter (#62074), Yandex AliceAI-Foundation-80B-A3B (#57963), Recursive Flint (40B MoE, 2.5B active) (#62938), Muse Spark Open (#61879), Step-5 Preview (#61727, #63147), NVIDIA Alpamayo 2 Super (#62957), Nemotron-Labs Dory1.0-4B (#60149), Nem…
vLLM v0.33.0
Signed-off-by: Micah Williamson micah.williamson@amd.com (cherry picked from commit 6d01893)
Signed-off-by: grYe99 guorongye99@gmail.com Co-authored-by: grYe99 guorongye99@gmail.com (cherry picked from commit bfa2a43)
[Bugfix][MRV2] Skip adaptive verification cost profiling in the CUDA …
v0.32.0 Highlights This release features 814 commits from 363 contributors (121 new)! Structured decisions and generic parsers: the new POST /v1/systemone endpoint answers choice, noul and score questions over a structured state (#59299), is served by default (#60677, #60696), and also runs on Cloudflare/clef-omni (#61064), LiquidAI/d1-3B (#60676) and DiffusionGemma (#60466). The new hf tool and r…
[Doc][RL] Document the weight-transfer HTTP protocol for trainers wit…
Signed-off-by: Vadim Gimpelson vadim.gimpelson@gmail.com Co-authored-by: Claude noreply@anthropic.com
[CI] Pin DeepSeek-V4.1-Flash-NVFP4 eval to its FP8-Engram revision (#…
vllm-proto 0.6.0
Signed-off-by: jinzhen.ljz jinzhen.ljz@antgroup.com Co-authored-by: Codex codex@openai.com Co-authored-by: Misha Goin mgoin64@gmail.com Co-authored-by: Kevin H. Luu khluu000@gmail.com
Signed-off-by: Matthew Bonanni mbonanni@redhat.com Co-authored-by: Claude Opus 5.5 noreply@anthropic.com
Release vllm-proto 0.5.0
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
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 SM100 default (#56935); DeepGEMM sparse MQA logits for the indexer (#56254) and Mega-Gate fusing the gate GEMM with expert selection (#56266); decoder boundaries fuse the TP all-reduce, mHC input preparation…
Signed-off-by: Isotr0py Isotr0py@outlook.com Co-authored-by: Harry Mellor 19981378+hmellor@users.noreply.github.com (cherry picked from commit 58b3298)
[Bugfix][HiSparse] Fix MTP acceptance collapse under FULL graphs with…
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] <37929162+mergify[bot]@users.noreply.github.com> Co-authored-by: Nick Hill nickhill123@gmail.com (cherry picked from commit e5e38ba)
Release vllm-proto 0.4.0
[Bugfix][Mamba] Keep the prompt-end prefill checkpoint under sparse r…
Signed-off-by: khluu khluu000@gmail.com Co-authored-by: Claude Opus 5.5 noreply@anthropic.com (cherry picked from commit aedaba8)
Signed-off-by: Andreas Karatzas akaratza@amd.com Co-authored-by: OpenAI Codex noreply@openai.com
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 FlashMLA V4.1 record on SM100 (#56893), DeepGEMM Mega-mHC (#56962), and async Engram prefetch with Engram DP sharding (#56512); DeepSeek-V4-Flash-Vision-Exp (#54566), also on ROCm (#55107) and with LoRA (#55897)…
[Bugfix][NIXL] Avoid receive reports for notification-only requests (…
Signed-off-by: jiahanc 173873397+jiahanc@users.noreply.github.com Co-authored-by: OpenAI Codex codex@openai.com
Release vllm-proto 0.3.0
Validated by PR #56538 CI at fa2a26f.
[watermarking] Dual-key gumbel-max watermarking for speculative decod…
vllm-proto 0.1.0
v0.29.0 Highlights This release features 594 commits from 277 contributors (91 new)! Model Runner V2 is now the default for all models (#53183), completing the rollout that began with pooling models (#48290). MRV2 also gained CUDA graph memory profiling for KV cache auto-sizing (#53306), batch-sharded sampling that cuts per-step logits memory by 1/TP (#50465), prompt embeds (#42963), extract_hidde…