V
v0.26.1rc0
[CI][ROCm] Fix test_ocp_mx_wikitext_correctness reference value (#4…
V
v0.26.0
vLLM v0.26.0 Release Notes Highlights This release features 411 commits from 212 contributors (61 new)! New Inkling model family with a full support stack: base modeling (#48799), piecewise CUDA graph support (#48822), Hopper FA4 relative attention (#48858), MTP=1 speculative decoding (#48869), LoRA (#48884), and standard ModelOpt NVFP4 quantization (#48990). DeepSeek-V4 performance push across ve…
V
v0.26.0rc1
v0.26.0rc1
V
v0.25.1
vLLM v0.25.1 Highlights This release features 2 commits from 2 contributors (1 new)! v0.25.1 is a patch release containing two targeted bug fixes on top of v0.25.0. Bug Fixes Avoid blocking model launching when no system FFmpeg is available for TorchCodec (#47888). Previously import torchcodec raised a RuntimeError at import time when system FFmpeg was missing, which blocked startup (e.g. vllm ser…
V
v0.25.0
vLLM v0.25.0 Release Notes Highlights This release features 558 commits from 232 contributors (64 new)! Model Runner V2 is now the default for all dense models (#44443). Building on quantized-model support from the previous release, MRv2 is now the standard execution path, with new support for EVS (#46535), realtime embeddings (#46762), prefix caching for Mamba hybrid models (#42406), multimodal-p…
V
v0.25.0rc3
[P/D][Bugfix] Fix PD async KV load lookahead handling for MTP spec de…
V
v0.25.0rc2
Fix embed scaling + CUDA graphs in Transformers modelling backend (#4…
V
v0.25.0rc1
[CPU][Bugfix] Fix flaky ShortConv prefill test on ARM (uninitialized …
V
v0.24.0
vLLM v0.24.0 Release Notes Highlights This release features 571 commits from 256 contributors (77 new)! MiniMax-M3: Added support for the new MiniMax-M3 model (#45381), with a fast follow-on of BF16/FP8 indexer via MSA (#45892), MXFP4 support (#45896), FP8 sparse GQA (#45744), and extensive AMD/ROCm tuning — mxfp8 MoE/linear on gfx950 (#45725), fp8_per_channel for bf16 weights on MI300X (#45854),…
V
v0.24.0rc2: Fix P/D with DP Supervisor (#46628)
Signed-off-by: Robert Shaw 114415538+robertgshaw2-redhat@users.noreply.github.com (cherry picked from commit c5e3c40)
V
v0.24.0rc1: [CI/Build] Fix topk histogram build on SM75 (#46550)
Signed-off-by: Mohammad Miadh Angkad 176301910+mmangkad@users.noreply.github.com (cherry picked from commit 191826e)
V
v0.23.0
vLLM v0.23.0 Release Notes Please note that Minimax M3 is not yet supported in this version. Please follow vLLM recipe for usage guides for M3. Highlights This release features 408 commits from 200 contributors (63 new)! DeepSeek-V4 matures across backends: Following its introduction in v0.22.0, DeepSeek-V4 received another large hardening and optimization pass. Its sparse MLA metadata is now deco…
V
v0.23.1rc0: [Bugfix][CI] Update Dockerfile dependency graph PNG (#45602)
Signed-off-by: sfeng33 4florafeng@gmail.com
V
v0.23.0rc2: [Docker] Fix CUTLASS DSL cu13 install order in Dockerfile (#45204)
Signed-off-by: Mohammad Miadh Angkad 176301910+mmangkad@users.noreply.github.com (cherry picked from commit 40e065e)
V
v0.22.1
Highlights This release features 8 commits from 6 contributors (1 new)! v0.22.1 is a patch release on top of v0.22.0 with targeted bug fixes plus a couple of additions: new model support for JetBrains' Mellum v2, zentorch-accelerated quantized linear inference on AMD Zen CPUs, and fixes for multi-node Ray data-parallel serving, DeepSeek-V4 initialization, and a few model-loading regressions. Model…
V
v0.22.1rc2: fix: resolve CUTLASS fmin compatibility for DeepSeek-V4 init
Signed-off-by: khluu khluu000@gmail.com
V
v0.22.1rc1: [docker] Stop using extra-index-url for flashinfer-jit-cache (#44366)
Signed-off-by: Kevin H. Luu khluu000@gmail.com
V
v0.22.1rc0: [CI] Make Model Executor test hangs fail fast with a traceback (#43971)
Signed-off-by: khluu khluu000@gmail.com Co-authored-by: Claude noreply@anthropic.com