Skip to content

Pull requests: vllm-project/vllm

New pull request New
1,272 Open 15,988 Closed
1,272 Open 15,988 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] fix SM check for Flashinfer TRTLLM MOE nvidia
#30314 opened Dec 9, 2025 by jiahanc Loading…
5 tasks
2
[Misc][Quantization] Clarify the intent of GGUF FusedMoE weight materialization
#30310 opened Dec 9, 2025 by a4lg Loading…
1 of 5 tasks
[DCP][Bugfix][CI] Fix accuracy issue of DCP when using FLASH_ATTN_MLA ready ONLY add when PR is ready to merge/full CI is needed v1
#30309 opened Dec 9, 2025 by FENP Loading…
3 of 5 tasks
4
[bugfix][quantization] fix quark qwen3 kv_cache quantization qwen Related to Qwen models ready ONLY add when PR is ready to merge/full CI is needed
#30308 opened Dec 9, 2025 by haoyangli-amd Loading…
5
[Model][Quantization] Fix / Add GGUF support for Qwen2 MoE models qwen Related to Qwen models
#30307 opened Dec 9, 2025 by a4lg Loading…
3 of 5 tasks
@Isotr0py
3
Fix incomplete response generation for tool call outputs deepseek Related to DeepSeek models fb-exported frontend meta-exported
#30304 opened Dec 9, 2025 by qandrew • Draft
6
[Bugfix] Qwen 3 VL Embedding loading qwen Related to Qwen models ready ONLY add when PR is ready to merge/full CI is needed
#30303 opened Dec 9, 2025 by noooop Loading…
5 tasks
1
4
[Misc] Pass reasoning to deepseekV32 tokenizer deepseek Related to DeepSeek models frontend
#30302 opened Dec 9, 2025 by kingsmad • Draft
5 tasks
2
[ResponsesAPI] Add GPTOSS MCP tool streaming frontend gpt-oss Related to GPT-OSS models
#30301 opened Dec 9, 2025 by qandrew Loading…
10
[Bugfix] Update WSL detection to check for WSL1 compatibility as WSL2…
#30299 opened Dec 9, 2025 by HoneyBerries Loading…
6
Main 20251205 amd ci/build ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm
#30298 opened Dec 9, 2025 by Alexei-V-Ivanov-AMD Loading…
7
[Core] Add SLA-tiered scheduling (opt-in) and docs documentation Improvements or additions to documentation v1
#30297 opened Dec 9, 2025 by ProdByBuddha Loading…
3 of 5 tasks
6
[CI/Build][Kernel][BugFix][AMD] Fix per_token_group_quant_fp8 to use correct fp8 min/max values and update atol/rtol in test_quantfp8_group_functionality rocm Related to AMD ROCm
#30292 opened Dec 9, 2025 by rasmith Loading…
3
[CI/Build][AMD] Fix ref_dynamic_per_token_quant reference implementation on ROCm. rocm Related to AMD ROCm
#30291 opened Dec 9, 2025 by rasmith Loading…
2
[Core] Add token-level KV cache metrics to V1 engine v1
#30289 opened Dec 9, 2025 by Minsung-commit Loading…
5
Adding quantized fused_moe_lora support
#30286 opened Dec 9, 2025 by yugong333 Loading…
5 tasks
5
Ensure minimum frames for GLM 4.6V compatibility
#30285 opened Dec 9, 2025 by gh-wf Loading…
1 of 3 tasks
5
[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 needs-rebase
#30280 opened Dec 8, 2025 by RunkaiTao • Draft
5 tasks
4
[CPU][Bugfix] Fix CPU Profiler issue v1
#30278 opened Dec 8, 2025 by zhili03 Loading…
7
[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…
6
[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
ProTip! What’s not been updated in a month: updated:<2025-11-08.