Skip to content

Pull requests: vllm-project/vllm

New pull request New
4,865 Open 30,693 Closed
4,865 Open 30,693 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 inverted text validation in FireRedASR2/FunASR processors bug Something isn't working
#54001 opened Aug 27, 2026 by hungnnvidia Contributor • Draft
[Bugfix] Ignore non-dict JSON in model redirect file bug Something isn't working
#54000 opened Aug 27, 2026 by hungnnvidia Contributor • Draft
[Bugfix] Raise clear error on interleaved multimodal placeholder overcount bug Something isn't working frontend
#53999 opened Aug 27, 2026 by hungnnvidia Contributor • Draft
[XPU][V2] Keep grammar-bitmask copies on the current stream under XPU graphs intel-gpu Related to Intel GPU mrv2 Model Runner V2 specific
#53997 opened Aug 27, 2026 by CySpiegel Loading…
1
1
[Quantization] Skip absent fused-layer shards in the GPTQ per-layer check (Gemma 4 k_eq_v) quantization
#53996 opened Aug 27, 2026 by CySpiegel Loading…
1
1
[ROCm] add AITER MLA prefill CI coverage ci/build rocm Related to AMD ROCm
#53995 opened Aug 27, 2026 by CuongTranXuan Loading…
1
1
fix: define math constants for FlashMLA MSVC builds ci/build
#53994 opened Aug 27, 2026 by CuongTranXuan Loading…
1
1
[Bugfix] Fix out-of-bounds attrIdxs in C++ batch memcpy path (cache_kernels.cu) bug Something isn't working
#53991 opened Aug 27, 2026 by Vikas8719 Loading…
4 tasks
1
2
[Bugfix][XPU] Fall back to torch query when getMemoryInfo reports zero free memory bug Something isn't working intel-gpu Related to Intel GPU
#53990 opened Aug 27, 2026 by CySpiegel Loading…
1
[Model][XPU] Enable fused QK-norm+RoPE+gate Triton kernel on XPU intel-gpu Related to Intel GPU qwen Related to Qwen models
#53989 opened Aug 27, 2026 by CySpiegel Loading…
1
[Spec Decode][ROCm] Add FLy: entropy-gated deferred verification for draft-model speculative decoding documentation Improvements or additions to documentation rocm Related to AMD ROCm speculative-decoding verified Run pre-commit for new contributors without triggering other tests
#53987 opened Aug 27, 2026 by eecspan Loading…
3
[XPU][CI] increase timeout of shutdown intel-gpu Related to Intel GPU
#53986 opened Aug 27, 2026 by zhenwei-intel Contributor • Draft
4 tasks
Fix: Prevent SageMaker logger standard from suppressing vLLM startup logs frontend
#53985 opened Aug 27, 2026 by DresdenGman Loading…
1
1
[Bugfix][DSpark] Skip unregistered DeepSeek-V4 expert weights bug Something isn't working deepseek Related to DeepSeek models dflash DSv4
#53984 opened Aug 27, 2026 by cr-zhao Contributor Loading…
4 tasks done
1
[Bugfix] Route directly constructed embeddings through CPU offload bug Something isn't working
#53981 opened Aug 27, 2026 by waizuichougou Loading…
1
1
[XPU][TEST]Add entrypoints test in Intel GPU CI ci/build intel-gpu Related to Intel GPU
#53980 opened Aug 27, 2026 by zxd1997066 Contributor Loading…
4 tasks done
[Attention][Spec Decode] NVFP4 KV: open the FA2 non-causal prefill wrapper for DFlash-family drafters (sm12x) dflash nvidia quantization
#53979 opened Aug 27, 2026 by TechPrototyper Loading…
1
[Bugfix][Spec Decode] DFlash2: survive spec warmup with unfilled draft buffers (embed outside compile; clamp selector gathers) bug Something isn't working dflash mrv2 Model Runner V2 specific qwen Related to Qwen models speculative-decoding
#53978 opened Aug 27, 2026 by TechPrototyper Loading…
1
[Bugfix][Spec Decode] Mask out-of-range input ids in VocabParallelEmbedding at tp_size==1 bug Something isn't working
#53977 opened Aug 27, 2026 by TechPrototyper Loading…
1
[Bugfix][Test] Fix off-by-one error in sampled token rank causing flaky logprobs test bug Something isn't working
#53976 opened Aug 27, 2026 by mayuyuace Contributor Loading…
Revert "[Bugfix][ROCm][Disagg] Fix MoRIIO shared KV memory region registration" (#53698) bug Something isn't working kv-connector rocm Related to AMD ROCm
#53974 opened Aug 27, 2026 by vllm-agent Contributor • Draft
[Model][Perf] Use broadcast mHC pre for DeepSeek V4 DSpark deepseek Related to DeepSeek models dflash DSv4
#53972 opened Aug 27, 2026 by liuyao0322 Loading…
4 tasks done
2
[Bugfix] Fix out-of-bounds attrIdxs in C++ batch memcpy path bug Something isn't working
#53971 opened Aug 27, 2026 by dzc2000 Loading…
1
1
[BUGFIX] Fix dflash batched token budget bug Something isn't working dflash mrv2 Model Runner V2 specific speculative-decoding
#53970 opened Aug 27, 2026 by Orvid Loading…
1
[Bugfix] Support NoPE models on FLASHINFER_MLA_SPARSE_SM120 and validate effective topk buffer width bug Something isn't working nvidia
#53969 opened Aug 27, 2026 by hamiltongaianimd Loading…
1
ProTip! Mix and match filters to narrow down what you’re looking for.