Skip to content

Pull requests: vllm-project/vllm

New pull request New
3,335 Open 25,247 Closed
3,335 Open 25,247 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

[Bugfix] Fix gridDim.y overflow for large row counts bug Something isn't working
#45255 opened Jun 11, 2026 by JasonLi314 Loading…
3 tasks done
1
1
[MM][CG] Support ViT full CUDA graph for Ernie-4.5-VL image inference documentation Improvements or additions to documentation multi-modality Related to multi-modality (#4194) nvidia
#45254 opened Jun 11, 2026 by qyYue1389 Contributor Loading…
1
docs: add fix disclosure policy to SECURITY.md documentation Improvements or additions to documentation
#45253 opened Jun 11, 2026 by jperezdealgaba Contributor Loading…
1
[Security] Fix DoS via prompt_embeds on M-RoPE models v1
#45252 opened Jun 11, 2026 by jperezdealgaba Contributor Loading…
[Bugfix] Restrict FlashInfer cuDNN FP8 ViT attention gate to Blackwell (SM 100) bug Something isn't working nvidia
#45251 opened Jun 11, 2026 by wentian-byte Loading…
1 of 3 tasks
4
[Bugfix][Frontend] Keep a reference to the background abort task in disagg api_router bug Something isn't working frontend
#45249 opened Jun 11, 2026 by kratos0718 Loading…
1
[Bugfix] Fix CPU memory leak in worker_busy_loop RPC deserialization path bug Something isn't working v1
#45248 opened Jun 11, 2026 by hiepnnguyentcu • Draft
3 of 4 tasks
1
1
[Tests][Reasoning] Add test coverage for Step3ReasoningParser
#45247 opened Jun 11, 2026 by z-priyanshu Loading…
1
[CI] Enable sccache for Rust build under CUDA/ROCm ci/build intel-gpu Related to Intel GPU nvidia ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm rust
#45246 opened Jun 11, 2026 by BugenZhao Member Loading…
4 tasks
2
[Bugfix] Pre-compile _zero_kv_blocks_kernel and _compute_slot_mapping_kernel during warmup bug Something isn't working
#45245 opened Jun 11, 2026 by z-priyanshu Loading…
2 of 3 tasks
1
1
minicpmv4_6: fix ImageSize (W,H) order for placeholder token calculation
#45244 opened Jun 11, 2026 by tc-mb Contributor Loading…
[RISC-V] Enable BF16 on VLEN=256 hardware ci/build cpu Related to CPU backends
#45243 opened Jun 11, 2026 by velonica0 Contributor Loading…
[Frontend] Add site-packages support for reasoning/tool parser plugins tool-calling
#45241 opened Jun 11, 2026 by odashi Loading…
2 of 4 tasks
1
[XPU][DeepSeek-V4] Fix MTP: sync with upstream fixes #44821 and #43746 deepseek Related to DeepSeek models intel-gpu Related to Intel GPU
#45240 opened Jun 11, 2026 by majian4work Contributor Loading…
1
fix(ep): use floor/ceil for n_local_physical_experts bookkeeping in DeepSeek-V2 and Qwen3-MoE ci/build cpu Related to CPU backends deepseek Related to DeepSeek models documentation Improvements or additions to documentation frontend needs-rebase nvidia qwen Related to Qwen models rocm Related to AMD ROCm v1
#45239 opened Jun 11, 2026 by max-amos • Draft
3
[Core] Avoid mixed batch on D-node using spec dec by isolating prefill-tail request v1
#45237 opened Jun 11, 2026 by qianlihuang Contributor • Draft
4 tasks
[ROCm] Enable ROCm Attention Sinks and Connector-Friendly KV Layouts documentation Improvements or additions to documentation kv-connector rocm Related to AMD ROCm v1
#45234 opened Jun 11, 2026 by AndreasKaratzas Member • Draft
1
Bump the minor-update group across 1 directory with 150 updates ci/build dependencies Pull requests that update a dependency file nvidia rocm Related to AMD ROCm
#45233 opened Jun 11, 2026 by dependabot Bot Loading…
[FlexAttention] make custom mask mods fully cudagraphable nvidia v1
#45232 opened Jun 11, 2026 by liangel-02 Contributor • Draft
[Bugfix][KV-transfer] MoRIIO: READ-mode stability fixes (completion IDs, DP routing, drain, keepalive) bug Something isn't working documentation Improvements or additions to documentation kv-connector v1
#45230 opened Jun 11, 2026 by chaeminlim-mb • Draft
3 of 4 tasks
4
[V1][Spec Decode] Relaxed acceptance for thinking-phase tokens (port of #22238) v1
#45229 opened Jun 11, 2026 by chaeminlim-mb • Draft
3 of 4 tasks
2
[Core][KV-transfer] MoRIIO: multi-node TP prefill→decode dispatch via published host list documentation Improvements or additions to documentation kv-connector
#45228 opened Jun 11, 2026 by chaeminlim-mb • Draft
3 of 4 tasks
4
[Bugfix][ROCm] MLA MTP decode: size verification metadata for real qlen/dtype, gate persistent path, fix CUDA-graph padding bug Something isn't working nvidia rocm Related to AMD ROCm v1
#45227 opened Jun 11, 2026 by chaeminlim-mb • Draft
5 tasks done
2
[ROCm][MoE] Route batched expert layout through flat-reshape wrapper for AITER FP8 rocm Related to AMD ROCm
#45226 opened Jun 11, 2026 by chaeminlim-mb • Draft
6 tasks done
2
[Bugfix][ROCm][MoE] MoRI: pass num_qp_per_pe/quant_type explicitly; preserve router top-k for finalize bug Something isn't working rocm Related to AMD ROCm
#45225 opened Jun 11, 2026 by chaeminlim-mb • Draft
4 tasks done
2
ProTip! no:milestone will show everything without a milestone.