[Versioning] Bump vllm from 0.28.0 to 0.30.0 in /sota-implementations/grpo by dependabot[bot] · Pull Request #4540 · pytorch/rl

dependabot · 2026-10-08T20:46:04Z

Bumps vllm from 0.28.0 to 0.30.0.

Release notes

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); GLM-5.3-Flash (#53906) with EPLB (#55119); K2-Horizon (#55063); Cohere Compass (#54774); Bailing V3 VL (#55921); Nanbeige4.2 via the Transformers backend (#56071); and a DeepSeek-V4 CPU backend with AVX512/AMX sparse MLA, indexer, mHC and compressor kernels (#55355).

Fast Start: a persistent per-GPU weight-cache daemon holds post-quantized, TP-sharded weights in GPU memory so restarting engines map them over CUDA IPC with --load-format ipc_cache instead of reloading from disk (#54921), now covering FP4 checkpoints (#55465) and multi-node TP (#55468).

Watermarking: Gumbel-max watermarked generation and detection with a keyed PRF, per-request opt-out and an example detection endpoint (#54053); dual-key Gumbel-max makes it compatible with speculative decoding (#56122); the Rust frontend forwards the per-request controls (#56338).

HiSparse: a host-resident tier for sparse-MLA decode that spills KV pages to pinned host memory under GPU pressure and serves top-k misses from a per-request GPU hot buffer, enabled through HiSparseConnector (#53781), with Prometheus counters (#56061), a host cache shared across TP ranks (#56629), and the attention config inferred from the connector (#57041).

Model Runner V2: dual-batch overlap in eager mode (#50945) and with FULL CUDA graphs for microbatched steps (#51700); MTP (#46994) and EAGLE3/DFlash/DSpark (#50514) speculative decoding under pipeline parallelism; adaptive verification for every draft-model speculator through an online acceptance estimator (#52228); gc frozen during graph capture, cutting capture from 12s to 2s and engine init from 28.9s to 8.2s on H200 (#54646); --return-sampling-mask compacted on GPU, fixing an about 2x RL step-time regression (#54901).

Qwen3.8-Flash-Next performance: separate prefill and decode QSA indexer kernels (#54513), fused PLE kernels (#54517), FP8 indexer cache (#54890), padded-index skipping in sparse GQA (#54873), fused PLE residual and QSA output gate (#55309), UVA PLE offload and Engram tensor parallelism via --engram-config (#54371), and torch.compile removed from the NVIDIA implementation so FP8 fits on a single GB300 (#55272).

Kimi K3 performance: native CUDA AttnRes default on SM100 (#54261), KDA mixed-batch gather/scatter removed (5.2-7.7% E2E throughput, #56159), grouped FP8 MLA cache insertion (4-6x kernel speedup at small batch, #55356), DSV3 low-latency GEMM on strided tensors (12-81% kernel speedup, #54565), overlapped TP8 KDA projections (#54697), FlashInfer KDA kernels (#55364), internal prefix checkpoints with partial prefix caching and speculative decoding (#53614), and symmetric DCP disaggregation for hybrid Mamba models (#55531).

Large scale serving: PCP+DCP on sparse-MLA models (#56157), PCP with single-module MTP and replicated DSpark (#56107) and decode-only FULL CUDA graphs (#53867), Elastic EP reusing CUDA graphs across reconfiguration (#54985), an opt-in FlashInfer PCIe IPC all-reduce for NVLink-less boxes (#53576), DeepEP v2 async finalize overlapping shared experts with combine (#52781), Mooncake Store heterogeneous TP sharing (#53129), a KVCR secondary-tier adapter (#53624), and encoder-cache sharing over NIXL (#47941) and Mooncake (#41567).

Quantization: targeted online quantization through quantization_config.targets (#51285) and on partially pre-quantized checkpoints from any quant method (#51392), W4A16 DSA with the nvfp4_fp8_ds_mla KV cache (#51724), FlashInfer CuTeDSL NVFP4 W4A16 default over Marlin on SM100/103 (#53014), NVFP4 in the torch linear backend (#53319), per-quantization linear backend overrides (#51204), AutoRound 2/3/5/6/7-bit on CUDA (#52890), and DeepSelect top-k for the DSA sparse indexer (#56464).

Breaking changes: scale-out endpoints are opt-in on plain vllm serve via --enable-scale-out, replacing VLLM_ENABLE_SCALE_OUT_ENDPOINTS (#54579, #55176); GPTQ activation ordering (g_idx) removed (#54809); items deprecated for 0.29 removed, including the VLLM_PREFIX_CACHE_RETENTION_INTERVAL and VLLM_MM_HASHER_ALGORITHM env vars (#55353); the all Mamba cache mode deprecated (#55041); python -m vllm.entrypoints.grpc_server deprecated in favor of vllm serve --grpc (#56746); YaRN aligned with Transformers so vendor YaRN aliases no longer re-scale max_model_len (#56446).

Release Artifacts

Python Wheels

Platform Install

PyPI (CUDA 13.0) pip install vllm

PyPI (CUDA 13.0, uv) uv pip install vllm --torch-backend=auto

ROCm pip install vllm --extra-index-url https://wheels.vllm.ai/rocm/0.30.0/rocm723

XPU uv pip install vllm --extra-index-url https://wheels.vllm.ai/0.30.0/xpu --extra-index-url https://download.pytorch.org/whl/xpu --index-strategy unsafe-best-match

Docker Images

Platform Docker Image

CUDA 13.0 (Default) docker pull vllm/vllm-openai:v0.30.0

CUDA 12.9 docker pull vllm/vllm-openai:v0.30.0-cu129

CUDA 13.0 + Ubuntu 24.04 docker pull vllm/vllm-openai:v0.30.0-ubuntu2404

CUDA 12.9 + Ubuntu 24.04 docker pull vllm/vllm-openai:v0.30.0-cu129-ubuntu2404

ROCm docker pull vllm/vllm-openai-rocm:v0.30.0

CPU docker pull vllm/vllm-openai-cpu:v0.30.0

XPU docker pull vllm/vllm-openai-xpu:v0.30.0

Other Artifacts

Pre-built release artifacts are available in the Assets section at the bottom of this page, including:

Source distribution tarball

CUDA 12.9 Python wheels for x86_64 and arm64

CUDA 13.0 Python wheels for x86_64 and arm64

CPU Python wheels for x86_64, arm64, and macOS

XPU Python wheel for x86_64

Model Support

... (truncated)

Commits

ced6857 [CI][Build] Harden triton-cpu sleef submodule fetch in CPU image build (#57871)
9ed533e [Build] Fix DeepGEMM CUDA 12.9 release builds (#57554)
fa6ff06 [Bugfix][NIXL] Avoid receive reports for notification-only requests (#57570)
526f127 [Bugfix][HiSparse][NIXL] Import full blocks without tail prefill on D (#57049)
4df23e6 [XPU] Fix incorrect context-key normalization for Qwen DFlash-based models (#...
a00a354 [Bugfix] Isolate supplemental FlashInfer BF16 autotuning (#57285)
201132e [Bugfix][HiSparse][PD] Align region-mapped pulls across logical block sizes (...
57105e3 [Bugfix] Make GPU sync checks safe under torch.compile (#56904)
69ca4a5 [Build][NVIDIA] Update public Rubin dependencies and MSA compatibility (#56545)
99a9381 [BugFix][PCP] Handle missing DP metadata in one-sided EP (#54016)
Additional commits viewable in compare view

pytorch-bot · 2026-10-08T20:46:10Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/4540

📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❌ 1 New Failure, 1 Unrelated Failure

As of commit a8b2948 with merge base 264a3c2 ():

NEW FAILURE - The following job has failed:

LLM Tests on Linux / unittests-vllm (3.12, 12.9) / linux-job (gh)
test/llm/test_vllm.py::TestAsyncVLLMIntegration::test_weight_updates_with_transformer

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

Unit-tests on Linux / tests-optdeps (3.12, 13.0) / linux-job (gh) (trunk failure)
RuntimeError: Command bash /__w/_temp/exec_script failed with exit code 2

This comment was automatically generated by Dr. CI and updates every 15 minutes.

github-actions · 2026-10-08T20:46:23Z

⚠️ PR Title Label Error

PR title must start with a label prefix in brackets (e.g., [BugFix]).

Current title: Bump vllm from 0.28.0 to 0.30.0 in /sota-implementations/grpo

Supported Prefixes (case-sensitive)

Your PR title must start with exactly one of these prefixes:

Prefix	Label Applied	Example
`[Algorithm]`	new algo	`[Algorithm] Add new RL objective`
`[BE]`	BE	`[BE] Improve error messages`
`[Benchmark]` or `[Benchmarks]`	Benchmarks	`[Benchmark] Add collector benchmark`
`[BugFix]`	BugFix	`[BugFix] Fix memory leak in collector`
`[Example]` or `[Examples]`	Examples	`[Example] Add training script`
`[Feature]`	Feature	`[Feature] Add new optimizer`
`[Doc]` or `[Docs]`	Documentation	`[Doc] Update installation guide`
`[Refactor]`	Refactoring	`[Refactor] Clean up module imports`
`[CI]`	CI	`[CI] Fix workflow permissions`
`[Test]` or `[Tests]`	Tests	`[Tests] Add unit tests for buffer`
`[Trainer]` or `[Trainers]`	Trainers	`[Trainer] Add trainer config`
`[Environment]` or `[Environments]`	Environments	`[Environments] Add Gymnasium support`
`[Data]`	Data	`[Data] Fix replay buffer sampling`
`[LLM]`	llm/	`[LLM] Add reward model integration`
`[Minor]`	small change	`[Minor] Fix typo in error message`
`[Performance]` or `[Perf]`	Performance	`[Performance] Optimize tensor ops`
`[BC-Breaking]`	bc breaking	`[BC-Breaking] Remove deprecated API`
`[Deprecation]`	Deprecation	`[Deprecation] Mark old function`
`[Algorithm]` or `[Algorithms]`	new algo	`[Algorithm] Add new objective`
`[Quality]`	Quality	`[Quality] Fix typos and add codespell`
`[Versioning]`	versioning	`[Versioning] Bump release version`
`[WIP]`	WIP	`[WIP] Draft implementation`

Note: Common variations like singular/plural are supported (e.g., [Doc] or [Docs]).

bsprenger · 2026-10-15T08:56:13Z

@dependabot rebase

Bumps [vllm](https://github.com/vllm-project/vllm) from 0.28.0 to 0.30.0. - [Release notes](https://github.com/vllm-project/vllm/releases) - [Commits](vllm-project/vllm@v0.28.0...v0.30.0) --- updated-dependencies: - dependency-name: vllm dependency-version: 0.30.0 dependency-type: direct:production ... Signed-off-by: dependabot[bot] <support@github.com>

github-actions · 2026-10-15T08:57:16Z

⚠️ PR Title Label Error

PR title must start with a label prefix in brackets (e.g., [BugFix]).

Current title: Bump vllm from 0.28.0 to 0.30.0 in /sota-implementations/grpo

Supported Prefixes (case-sensitive)

Your PR title must start with exactly one of these prefixes:

Prefix	Label Applied	Example
`[Algorithm]`	new algo	`[Algorithm] Add new RL objective`
`[BE]`	BE	`[BE] Improve error messages`
`[Benchmark]` or `[Benchmarks]`	Benchmarks	`[Benchmark] Add collector benchmark`
`[BugFix]`	BugFix	`[BugFix] Fix memory leak in collector`
`[Example]` or `[Examples]`	Examples	`[Example] Add training script`
`[Feature]`	Feature	`[Feature] Add new optimizer`
`[Doc]` or `[Docs]`	Documentation	`[Doc] Update installation guide`
`[Refactor]`	Refactoring	`[Refactor] Clean up module imports`
`[CI]`	CI	`[CI] Fix workflow permissions`
`[Test]` or `[Tests]`	Tests	`[Tests] Add unit tests for buffer`
`[Trainer]` or `[Trainers]`	Trainers	`[Trainer] Add trainer config`
`[Environment]` or `[Environments]`	Environments	`[Environments] Add Gymnasium support`
`[Data]`	Data	`[Data] Fix replay buffer sampling`
`[LLM]`	llm/	`[LLM] Add reward model integration`
`[Minor]`	small change	`[Minor] Fix typo in error message`
`[Performance]` or `[Perf]`	Performance	`[Performance] Optimize tensor ops`
`[BC-Breaking]`	bc breaking	`[BC-Breaking] Remove deprecated API`
`[Deprecation]`	Deprecation	`[Deprecation] Mark old function`
`[Algorithm]` or `[Algorithms]`	new algo	`[Algorithm] Add new objective`
`[Quality]`	Quality	`[Quality] Fix typos and add codespell`
`[Versioning]`	versioning	`[Versioning] Bump release version`
`[WIP]`	WIP	`[WIP] Draft implementation`

Note: Common variations like singular/plural are supported (e.g., [Doc] or [Docs]).

github-actions · 2026-10-15T08:57:16Z

⚠️ PR Title Label Error

PR title must start with a label prefix in brackets (e.g., [BugFix]).

Current title: Bump vllm from 0.28.0 to 0.30.0 in /sota-implementations/grpo

Supported Prefixes (case-sensitive)

Your PR title must start with exactly one of these prefixes:

Prefix	Label Applied	Example
`[Algorithm]`	new algo	`[Algorithm] Add new RL objective`
`[BE]`	BE	`[BE] Improve error messages`
`[Benchmark]` or `[Benchmarks]`	Benchmarks	`[Benchmark] Add collector benchmark`
`[BugFix]`	BugFix	`[BugFix] Fix memory leak in collector`
`[Example]` or `[Examples]`	Examples	`[Example] Add training script`
`[Feature]`	Feature	`[Feature] Add new optimizer`
`[Doc]` or `[Docs]`	Documentation	`[Doc] Update installation guide`
`[Refactor]`	Refactoring	`[Refactor] Clean up module imports`
`[CI]`	CI	`[CI] Fix workflow permissions`
`[Test]` or `[Tests]`	Tests	`[Tests] Add unit tests for buffer`
`[Trainer]` or `[Trainers]`	Trainers	`[Trainer] Add trainer config`
`[Environment]` or `[Environments]`	Environments	`[Environments] Add Gymnasium support`
`[Data]`	Data	`[Data] Fix replay buffer sampling`
`[LLM]`	llm/	`[LLM] Add reward model integration`
`[Minor]`	small change	`[Minor] Fix typo in error message`
`[Performance]` or `[Perf]`	Performance	`[Performance] Optimize tensor ops`
`[BC-Breaking]`	bc breaking	`[BC-Breaking] Remove deprecated API`
`[Deprecation]`	Deprecation	`[Deprecation] Mark old function`
`[Algorithm]` or `[Algorithms]`	new algo	`[Algorithm] Add new objective`
`[Quality]`	Quality	`[Quality] Fix typos and add codespell`
`[Versioning]`	versioning	`[Versioning] Bump release version`
`[WIP]`	WIP	`[WIP] Draft implementation`

Note: Common variations like singular/plural are supported (e.g., [Doc] or [Docs]).

dependabot Bot added Dependencies Pull requests that update a dependency file python Pull requests that update python code labels Oct 8, 2026

meta-cla Bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Oct 8, 2026

github-actions Bot added the sota-implementations/ label Oct 8, 2026

bsprenger changed the title ~~Bump vllm from 0.28.0 to 0.30.0 in /sota-implementations/grpo~~ [Versioning] Bump vllm from 0.28.0 to 0.30.0 in /sota-implementations/grpo Oct 15, 2026

github-actions Bot added the versioning Versioning change (version number etc) label Oct 15, 2026

dependabot Bot changed the title ~~[Versioning] Bump vllm from 0.28.0 to 0.30.0 in /sota-implementations/grpo~~ Bump vllm from 0.28.0 to 0.30.0 in /sota-implementations/grpo Oct 15, 2026

dependabot Bot force-pushed the dependabot/pip/sota-implementations/grpo/vllm-0.30.0 branch from c72fd55 to ee3d338 Compare October 15, 2026 08:57

bsprenger added the llm/ LLM-related PR, triggers LLM CI tests label Oct 15, 2026

bsprenger changed the title ~~Bump vllm from 0.28.0 to 0.30.0 in /sota-implementations/grpo~~ [Versioning] Bump vllm from 0.28.0 to 0.30.0 in /sota-implementations/grpo Oct 15, 2026

[CI] Test LLM integration with vLLM 0.30.0

7667eac

github-actions Bot added the CI Has to do with CI setup (e.g. wheels & builds, tests...) label Oct 15, 2026

bsprenger added the ci-refresh-hf-cache label Oct 15, 2026

[CI] Run vLLM integration tests without hiding setup failures

447d6a9

bsprenger changed the title ~~[Versioning] Bump vllm from 0.28.0 to 0.30.0 in /sota-implementations/grpo~~ [Versioning] Bump vLLM to 0.30.0 and validate LLM integration Oct 15, 2026

bsprenger added the ci/optdeps Run the full tests-optdeps suite on this PR label Oct 15, 2026

[CI] Restore the existing LLM runner allocation

a8b2948

bsprenger changed the title ~~[Versioning] Bump vLLM to 0.30.0 and validate LLM integration~~ [Versioning] Bump vllm from 0.28.0 to 0.30.0 in /sota-implementations/grpo Oct 15, 2026

bsprenger approved these changes Oct 15, 2026

View reviewed changes

Navigation Menu

Repository navigation

[Versioning] Bump vllm from 0.28.0 to 0.30.0 in /sota-implementations/grpo - #4540

[Versioning] Bump vllm from 0.28.0 to 0.30.0 in /sota-implementations/grpo#4540
dependabot[bot] wants to merge 4 commits into
mainfrom
dependabot/pip/sota-implementations/grpo/vllm-0.30.0

dependabot Bot commented on behalf of github Oct 8, 2026 •

edited by bsprenger

Loading

Uh oh!

pytorch-bot Bot commented Oct 8, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Oct 8, 2026

Uh oh!

bsprenger commented Oct 15, 2026

Uh oh!

github-actions Bot commented Oct 15, 2026

Uh oh!

github-actions Bot commented Oct 15, 2026

Uh oh!

This branch has not been deployed

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Platform	Install
PyPI (CUDA 13.0)	`pip install vllm`
PyPI (CUDA 13.0, uv)	`uv pip install vllm --torch-backend=auto`
ROCm	`pip install vllm --extra-index-url https://wheels.vllm.ai/rocm/0.30.0/rocm723`
XPU	`uv pip install vllm --extra-index-url https://wheels.vllm.ai/0.30.0/xpu --extra-index-url https://download.pytorch.org/whl/xpu --index-strategy unsafe-best-match`

Platform	Docker Image
CUDA 13.0 (Default)	`docker pull vllm/vllm-openai:v0.30.0`
CUDA 12.9	`docker pull vllm/vllm-openai:v0.30.0-cu129`
CUDA 13.0 + Ubuntu 24.04	`docker pull vllm/vllm-openai:v0.30.0-ubuntu2404`
CUDA 12.9 + Ubuntu 24.04	`docker pull vllm/vllm-openai:v0.30.0-cu129-ubuntu2404`
ROCm	`docker pull vllm/vllm-openai-rocm:v0.30.0`
CPU	`docker pull vllm/vllm-openai-cpu:v0.30.0`
XPU	`docker pull vllm/vllm-openai-xpu:v0.30.0`

Conversation

dependabot Bot commented on behalf of github Oct 8, 2026 • edited by bsprenger Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

v0.30.0

Highlights

Release Artifacts

Python Wheels

Docker Images

Other Artifacts

Model Support

Uh oh!

pytorch-bot Bot commented Oct 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/4540

❌ 1 New Failure, 1 Unrelated Failure

Uh oh!

github-actions Bot commented Oct 8, 2026

⚠️ PR Title Label Error

Supported Prefixes (case-sensitive)

Uh oh!

bsprenger commented Oct 15, 2026

Uh oh!

github-actions Bot commented Oct 15, 2026

⚠️ PR Title Label Error

Supported Prefixes (case-sensitive)

Uh oh!

github-actions Bot commented Oct 15, 2026

⚠️ PR Title Label Error

Supported Prefixes (case-sensitive)

Uh oh!

This branch has not been deployed

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

dependabot Bot commented on behalf of github Oct 8, 2026 •

edited by bsprenger

Loading

pytorch-bot Bot commented Oct 8, 2026 •

edited

Loading