Skip to content

Pull requests: vllm-project/vllm

New pull request New
3,036 Open 24,063 Closed
3,036 Open 24,063 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

fix: parse input_audio payloads with uuid frontend
#43451 opened May 22, 2026 by he-yufeng Contributor Loading…
1
3
[Formatting] Collapse multi-line arg lists where possible ci/build cpu Related to CPU backends deepseek Related to DeepSeek models documentation Improvements or additions to documentation frontend gpt-oss Related to GPT-OSS models intel-gpu Related to Intel GPU kv-connector llama Related to Llama models mistral Related to Mistral models multi-modality Related to multi-modality (#4194) needs-rebase new-model Requests to new models nvidia performance Performance-related issues qwen Related to Qwen models rocm Related to AMD ROCm speculative-decoding structured-output tool-calling tpu Related to Google TPUs v1
#43449 opened May 22, 2026 by njhill Member • Draft
@sangstar
2
[Bugfix] Make openai_serving_render optional in OpenAIServingChat and OpenAIServingCompletion bug Something isn't working frontend
#43448 opened May 22, 2026 by iOptimizeThings Loading…
3 of 4 tasks
1
1
[Prefix Caching] DeepSeekv4 only retain sliding window cache at specified interval boundaries deepseek Related to DeepSeek models v1
#43447 opened May 22, 2026 by wzhao18 Contributor • Draft
4 tasks
[Spec Decode] Allow causal DFlash speculative-decoding v1
#43445 opened May 22, 2026 by benchislett Member Loading…
[Bugfix][DeepseekV4] Harden compress_ratio fallback for transformers >=4.57 bug Something isn't working deepseek Related to DeepSeek models
#43443 opened May 22, 2026 by varjoranta Loading…
1
3
[Bugfix][DeepseekV4] Gate expert weight load on success bug Something isn't working deepseek Related to DeepSeek models
#43442 opened May 22, 2026 by varjoranta Loading…
1
2
[Docs] Fix incorrect docstring for all_non_structural_tag_constraints_none
#43441 opened May 22, 2026 by jrajath94 Loading…
1
[Model] Refactor Gemma4 vision tower with vLLM-native modules
#43440 opened May 22, 2026 by linitra24 Contributor Loading…
4 tasks
3
Enable FlashInfer checkpointing SSU STP no-fallback path needs-rebase v1
#43439 opened May 22, 2026 by danielafrimi Contributor • Draft
5
Update FastAPI dependency to exclude fastapi-cloud-cli ci/build
#43438 opened May 22, 2026 by ducviet00 Contributor Loading…
3
[Bugfix][Async][SpecDecode] Fix async MTP placeholder draft token handling bug Something isn't working v1
#43434 opened May 22, 2026 by SorenDreano Contributor Loading…
3 of 4 tasks
3
Keep scheduler alive for delayed KV connector frees v1 verified Run pre-commit for new contributors without triggering other tests
#43433 opened May 22, 2026 by lucifer1004 Loading…
6
[TurboQuant] Use MSE quantization for values v1
#43432 opened May 22, 2026 by lesj0610 Contributor Loading…
3 of 4 tasks
2
[Model] Add hotwords support for model Qwen3-ASR documentation Improvements or additions to documentation qwen Related to Qwen models
#43430 opened May 22, 2026 by homepy Loading…
4 tasks done
8
[rust] fix: aggregate is_sleeping and reset_prefix_cache across DP engines needs-rebase rust
#43429 opened May 22, 2026 by willamhou Loading…
2 tasks done
6
[Bugfix] Fix hash topk dtype mismatch bug Something isn't working
#43425 opened May 22, 2026 by wangyicong52 Loading…
@jeejeelee
1
[V1][Bugfix] structured_output × spec-decode: pre-commit grammar filter for boundary-step bonus tokens bug Something isn't working structured-output v1
#43424 opened May 22, 2026 by adammoisa Loading…
3 tasks
1
5
[Model] Add get_mm_max_tokens_per_item for GLM4_1V ProcessingInfo to avoid slow dummy inputs in launch model
#43422 opened May 22, 2026 by labAxiaoming Contributor Loading…
4 tasks
2
[XPU][Mamba] Triton-based selective scan forward op for XPU intel-gpu Related to Intel GPU
#43421 opened May 22, 2026 by mfylcek Contributor Loading…
5
Fix OLMo3 sliding attention RoPE parameters
#43419 opened May 22, 2026 by joanvelja • Draft
1
fix(benchmark): correct SpecBench.sample method signature to suppor… performance Performance-related issues
#43418 opened May 22, 2026 by JericRui Loading…
3
[Rust Frontend] Improve startup failure reporting UX frontend ready ONLY add when PR is ready to merge/full CI is needed rust v1
#43417 opened May 22, 2026 by BugenZhao Member Loading…
4 tasks
[Bugfix][Frontend] Fix input_audio parsing when uuid is present bug Something isn't working frontend ready ONLY add when PR is ready to merge/full CI is needed
#43414 opened May 22, 2026 by ffggs Loading…
1
5
[CI] Fix recurring NCCL workspace leak on subprocess engine shutdown v1
#43413 opened May 22, 2026 by haosdent Contributor • Draft
3
ProTip! What’s not been updated in a month: updated:<2026-04-22.