Skip to content

Pull requests: vllm-project/vllm

New pull request New
1,239 Open 15,252 Closed
1,239 Open 15,252 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

[Perf] Early return in KVCacheManager.allocate_slots v1
#29206 opened Nov 21, 2025 by Jialin • Draft
3 of 5 tasks
[CI/Build] Add terratorch for AMD ci/build rocm Related to AMD ROCm
#29205 opened Nov 21, 2025 by rjrock Loading…
3 of 5 tasks
3
[CI/Build] Disable test_gptoss_tp.py in 'LoRA TP Test' group for ROCm platform ci/build gpt-oss Related to GPT-OSS models rocm Related to AMD ROCm
#29204 opened Nov 21, 2025 by qli88 Loading…
1
[CI] Bug: Fix triton import issue force-merge ready ONLY add when PR is ready to merge/full CI is needed v1
#29202 opened Nov 21, 2025 by yewentao256 Loading…
1
[CI/Build] Replace COPY scripts with bind mounts to reduce layers ci/build
#29201 opened Nov 21, 2025 by mirzaim Loading…
5 tasks
6
Display warning only when ROCm version is less than Pytorch required version ci/build rocm Related to AMD ROCm
#29200 opened Nov 21, 2025 by Inokinoki Loading…
5 tasks
2
[amd][ci] update mteb version for ROCM ci/build rocm Related to AMD ROCm
#29199 opened Nov 21, 2025 by bradleyhd • Draft
5 tasks
[Model] Restore Gemma3 GGUF multimodal support with GGUF-only guards v1
#29198 opened Nov 21, 2025 by lucianommartins Loading…
9 tasks done
6
[Frontend] Implement robust video frame recovery for corrupted videos documentation Improvements or additions to documentation multi-modality Related to multi-modality (#4194) performance Performance-related issues
#29197 opened Nov 21, 2025 by vSeamar • Draft
5 tasks
3
[not for land] online fp8 quant with streaming weight post-processing
#29196 opened Nov 21, 2025 by vkuzo Loading…
5 tasks
5
[Build/CI][DP/EP] Add QWen/Qwen3-30B-A3B-FP8 + EPLB tests to Nightly H100 and B200 ci/build qwen Related to Qwen models
#29195 opened Nov 21, 2025 by varun-sundar-rabindranath Loading…
8
[Model Runner V2] Change bookkeeping logic in preparation for spec decoding nvidia v1
#29194 opened Nov 21, 2025 by WoosukKwon • Draft
1
[perf][cpu] Accelerate attention GEMMs (QK, PV) on Arm CPUs with NEON aarch64-cpu performance Performance-related issues ready ONLY add when PR is ready to merge/full CI is needed v1
#29193 opened Nov 21, 2025 by fadara01 Loading…
2 tasks
1
4
[Models] Lfm2-VL Architecture documentation Improvements or additions to documentation new-model Requests to new models
#29191 opened Nov 21, 2025 by paulpak58 Loading…
5 tasks
5
Fix: Resolve circular import in model_loader/utils.py
#29189 opened Nov 21, 2025 by nandan2003 Loading…
1
3
[Doc] Update more docs with respect to V1 documentation Improvements or additions to documentation
#29188 opened Nov 21, 2025 by DarkLight1337 Loading…
5 tasks
10
[LoRA] Cleanup FusedMoEWithLoRA
#29187 opened Nov 21, 2025 by jeejeelee Loading…
5 tasks
7
[Misc] Further clean up chunked prefill and prefix caching init ready ONLY add when PR is ready to merge/full CI is needed v1
#29186 opened Nov 21, 2025 by DarkLight1337 Loading…
5 tasks
7
[Core] NGram GPU Implementation compatible with Async Scheduler speculative-decoding v1
#29184 opened Nov 21, 2025 by PatchouliTIS • Draft
5 tasks
Add fused MoE config for H200 E160 N192 fp8
#29182 opened Nov 21, 2025 by FlintyLemming Loading…
3 of 5 tasks
1
[Frontend][Responses API] Multi-turn (with type: "output_text") support for non-harmony requests frontend gpt-oss Related to GPT-OSS models
#29175 opened Nov 21, 2025 by madskildegaard Loading…
3 tasks done
7
docs: fixes distributed executor backend config for multi-node vllm documentation Improvements or additions to documentation
#29173 opened Nov 21, 2025 by michaelact Loading…
5 tasks
2
[docs] Fix cudagraph mode config documentation Improvements or additions to documentation nvidia ready ONLY add when PR is ready to merge/full CI is needed
#29170 opened Nov 21, 2025 by angelayi Loading…
4
[BugFix] Call Base Layer Directly if LoRA A/B in Parallel Vocab are 0
#29167 opened Nov 21, 2025 by alex-jw-brooks Loading…
5 tasks
6
[Core] Add xxHash as a high-performance hash option for accelerating prefix caching ci/build deepseek Related to DeepSeek models documentation Improvements or additions to documentation frontend gpt-oss Related to GPT-OSS models kv-connector llama Related to Llama models multi-modality Related to multi-modality (#4194) 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 v1
#29163 opened Nov 21, 2025 by LuminolT Loading…
4 of 5 tasks
18
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.