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]: auto_round (INC) path hardcodes lm_head_quantized=False, crashing on checkpoints with quantized lm_head that auto-round legally produces
- [Bug]: Nemotron model CUDA error: an illegal memory access was encountered
- [Bug] Inkling on sm_121a (GB10): unclamped q-row in rel-bias score-mod gather causes deterministic illegal address (coredump evidence); + aux-stream KV-write race in fused_qkvr_prep
- [Bugfix] Fix false boolean values in YAML CLI configuration
- [Quant] Add online NVFP4 dense-linear quantization (W4A16 + W4A4)
- [Bug]: MiniMax-M3 NVFP4 produces garbage output + CUDA illegal memory access on Hopper (sm90) via Marlin FP4-MoE
- [Bug]: --linear-backend=flashinfer_b12x crashes on Qwen3.6-35B-A3B-NVFP4 — no kernel for FP8-quantized GDN QKVZ layer
- TRITON_ATTN support for KV cache dtype fp8 on SM75 to pre-SM89
- [Perf] fused_moe: load B weights via TMA tensor descriptor on SM90+
- fix(security): validate allowed_token_ids against model output vocab size
- Docs
- Python not yet supported