Skip to content

Pull requests: vllm-project/vllm

New pull request New
4,484 Open 29,780 Closed
4,484 Open 29,780 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[ROCm][DSv4] Enable DSpark adaptive verification deepseek Related to DeepSeek models rocm Related to AMD ROCm
#52362 opened Aug 14, 2026 by tuukkjs Contributor • Draft
Preserve deferred layerwise reload weights quantization
#52361 opened Aug 14, 2026 by mxinO • Draft
1
[MRV2][Metrics] Support CUDAGraphStat in MRV2 mrv2 Model Runner V2 specific nvidia
#52358 opened Aug 14, 2026 by yiz-liu Contributor Loading…
4 tasks
[Bugfix][DSv4] SM12x Triton fallback for fp8_einsum / o_proj (#43743) bug Something isn't working
#52357 opened Aug 14, 2026 by ajwharton • Draft
3 of 4 tasks
1
3
[Bugfix][ROCm] Skip FP8 MLA prefill PS-metadata build for chunked-context batches bug Something isn't working ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm
#52356 opened Aug 14, 2026 by shantipriya-amd Contributor Loading…
3 of 4 tasks
4
[hw-agnostic] Adding embedding layer and lm_head
#52355 opened Aug 14, 2026 by bohnstingl Contributor Loading…
3 of 4 tasks
[CI] Shard Hybrid SSM NixlConnector PD accuracy tests into 4 config groups ci/build kv-connector
#52354 opened Aug 14, 2026 by khluu Member • Draft
[CI] Split Spec Decode MTP nightly acceptance job into 2 shards ci/build
#52353 opened Aug 14, 2026 by khluu Member • Draft
[CI] Split MoE Refactor Integration Test (H100) config list across 4 shards ci/build
#52352 opened Aug 14, 2026 by khluu Member • Draft
[CI] Expand Basic Models (Extra Initialization) to 14 shards (<20 min) ci/build
#52351 opened Aug 14, 2026 by khluu Member • Draft
[CI] Shard LoRA TP (Distributed) into 4 timing-balanced groups ci/build
#52350 opened Aug 14, 2026 by khluu Member • Draft
[CI] Shard Kernels (B200) into 3 timing-balanced command buckets (<20 min) ci/build
#52349 opened Aug 14, 2026 by khluu Member • Draft
[CI] Shard Async Engine/Inputs/Utils/Worker/Config (CPU) into 4 timing-balanced groups ci/build
#52348 opened Aug 14, 2026 by khluu Member • Draft
[CI] Shard PyTorch fullgraph tests ci/build
#52345 opened Aug 14, 2026 by khluu Member • Draft
[CI] Shard v1 core, KV, and metrics ci/build
#52346 opened Aug 14, 2026 by khluu Member • Draft
[CI] Shard entrypoints API server ci/build
#52344 opened Aug 14, 2026 by khluu Member • Draft
[CI] Shard model runner v2 spec decode ci/build mrv2 Model Runner V2 specific
#52342 opened Aug 14, 2026 by khluu Member • Draft
[CI] Shard entrypoints pooling ci/build
#52343 opened Aug 14, 2026 by khluu Member • Draft
[CI] Shard Kernels Quantization Test to 6 shards, pin AMD mirror at 2 (<20 min) ci/build quantization rocm Related to AMD ROCm
#52341 opened Aug 14, 2026 by khluu Member • Draft
[CI] Shard Kernels Attention Test to 7 shards, pin AMD mirror at 2 (<20 min) ci/build rocm Related to AMD ROCm
#52340 opened Aug 14, 2026 by khluu Member • Draft
[CI] Shard multimodal standard 4 tests ci/build
#52338 opened Aug 14, 2026 by khluu Member • Draft
[CI] Shard hybrid language model tests ci/build
#52337 opened Aug 14, 2026 by khluu Member • Draft
[CI] Shard multimodal processor tests ci/build
#52336 opened Aug 14, 2026 by khluu Member • Draft
[CI] Shard multimodal extended generation 3 ci/build
#52335 opened Aug 14, 2026 by khluu Member • Draft
[CI] Shard multimodal extended pooling tests ci/build
#52334 opened Aug 14, 2026 by khluu Member • Draft
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.