vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: FlashInfer builder ValueError 'provided out is the wrong size for the accumulation' with Llama-4 chunked local attention when a prefill exceeds attention_chunk_size and max_num_seqs is small
- [Bug]: tool_choice: "required" causes xgrammar FSM crash / infinite hang with GLM-5.2-NVFP4 on vLLM 0.26.0
- [Perf] DSD arms pay a large baseline tax vs no-spec under production defaults; PIECEWISE override identified as one factor
- [Bug]: Multimodal models fail to load on ROCm/RDNA4 (gfx1201) — `CUDA error: invalid argument` in `vit_torch_sdpa_wrapper` encoder attention
- [Bugfix] Plumb SwiGLU-OAI gemm1 alpha/beta for ModelOpt NVFP4 MoE
- [Bug]: v0.26.0 EngineCore fails to start on SM90+ — _warmup_ll_bf16_router_gemm hits AttributeError: module 'cutlass.cute.core' has no attribute 'ThrMma' (nvidia-cutlass-dsl 4.6.0)
- [Bug]: VLLM_WSL2_ENABLE_PIN_MEMORY=1 is silently ignored on the ROCm platform
- [Kernel] Guard A8 Marlin repack K alignment
- [Bugfix][ROCm] Honor VLLM_WSL2_ENABLE_PIN_MEMORY on the ROCm platform
- [Bug]: Inkling parser is wrong for non reasoning mode - outputs "<|end_message|>"
- Docs
- Python not yet supported