Skip to content

Pull requests: vllm-project/vllm

New pull request New
1,269 Open 15,971 Closed
1,269 Open 15,971 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 compressed-tensors models failing to load with transformers backend bug Something isn't working quantization ready ONLY add when PR is ready to merge/full CI is needed
#30287 opened Dec 9, 2025 by mgoin Loading…
5 tasks
4
Adding quantized fused_moe_lora support
#30286 opened Dec 9, 2025 by yugong333 Loading…
5 tasks
4
Ensure minimum frames for GLM 4.6V compatibility
#30285 opened Dec 9, 2025 by gh-wf Loading…
1 of 3 tasks
4
[BugFix] Lazy tokenizer init in StructuredOutputManager to prevent GGUF semaphore leak structured-output v1
#30284 opened Dec 9, 2025 by kitaekatt Loading…
4 tasks
6
[Small] Add comment for parallel_config in FusedMoEModularKernel
#30282 opened Dec 8, 2025 by yewentao256 • Draft
[CI/Build] Ignore data_parallel_size_local
#30281 opened Dec 8, 2025 by rjrock Loading…
3 of 5 tasks
2
Add moe_align_block_size_no_permute for small batch size with large num_expert
#30280 opened Dec 8, 2025 by RunkaiTao • Draft
5 tasks
3
[CPU][Bugfix] Fix CPU Profiler issue v1
#30278 opened Dec 8, 2025 by zhili03 Loading…
6
[BugFix] Fix non detected failing tests ci/build ready ONLY add when PR is ready to merge/full CI is needed
#30277 opened Dec 8, 2025 by ilmarkov Loading…
5 tasks
4
[ROCM][CI] Fix AMD Examples Test Group ci/build documentation Improvements or additions to documentation rocm Related to AMD ROCm
#30276 opened Dec 8, 2025 by Concurrensee Loading…
5
[NIXL] refine decoder side post process for heterogeneous BlockSize and kv_layout kv-connector v1
#30275 opened Dec 8, 2025 by xuechendi Loading…
5 tasks
6
[AMD] Amd/deepseek aiter fusions deepseek Related to DeepSeek models needs-rebase rocm Related to AMD ROCm v1
#30274 opened Dec 8, 2025 by k50112113 • Draft
7
[Bugfix] Temporarily disable group quant rms norm fusion
#30273 opened Dec 8, 2025 by ElizaWszola Loading…
7
[CI/Build] Use spawn subprocess for ROCm documentation Improvements or additions to documentation rocm Related to AMD ROCm
#30272 opened Dec 8, 2025 by rjrock Loading…
3 of 5 tasks
1
[ROCm][CI][Bugfix] Multi-Modal Model Support Fixes and Attention Backend Improvements ci/build multi-modality Related to multi-modality (#4194) qwen Related to Qwen models rocm Related to AMD ROCm
#30270 opened Dec 8, 2025 by AndreasKaratzas Loading…
12
[Frontend] Fixes anthropic streaming message_start usage nesting frontend ready ONLY add when PR is ready to merge/full CI is needed
#30266 opened Dec 8, 2025 by bbartels Loading…
5 tasks
2
Fix 500 /tokenize errors and 400 v1/chat/completions errors when using truncate_prompt_tokens and sending /tokenize and v1/chat/completions requests under high concurrency frontend
#30264 opened Dec 8, 2025 by Soufiane-Ra Loading…
5
Multiple Hybrid KV Cache Coordinator v1
#30263 opened Dec 8, 2025 by roikoren755 Loading…
3 of 5 tasks
@heheda12345
2
Support TP which is not divded for NVFP4 kernels (flashinfer-cutlass) by adding dynamic padding nvidia
#30260 opened Dec 8, 2025 by danielafrimi Loading…
6
[Feature]: OpenTelemetry Metrics Support v1
#30258 opened Dec 8, 2025 by mladjan-gadzic • Draft
3 of 5 tasks
4
[bugfix][quantization] Fix fp8 per_tensor scale shape ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm v1
#30257 opened Dec 8, 2025 by haoyangli-amd Loading…
[ROCm] Use aiter.topk_sigmoid in llama4 llama Related to Llama models rocm Related to AMD ROCm
#30255 opened Dec 8, 2025 by tpopp Loading…
8
gptq marlin quantization support for fused moe with lora
#30254 opened Dec 8, 2025 by Bhanu068 Loading…
3 of 5 tasks
4
fix: DeepSeek-V3.2 DeepGEMM RuntimeError deepseek Related to DeepSeek models
#30251 opened Dec 8, 2025 by KeeProMise Loading…
5 tasks
5
[gpt-oss] Add model_identity to system message retrieval for harmony chat template frontend gpt-oss Related to GPT-OSS models
#30247 opened Dec 8, 2025 by lyuwen Loading…
5 tasks
5
ProTip! no:milestone will show everything without a milestone.