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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Tracking] TurboQuant + Gemma 4 multimodal: 5-gate blocker stack
- [Refactor] Remove torch 2.9, 2.10 workround
- fused_add_rms_norm does not branch on has_weight=False (TODO(luka)); FlashNorm weightless RMSNorm cannot realize a speedup on the GPU path
- [Bug]: macOS arm64 build broken — `cpu_attn_vec.hpp` calls `FP32Vec16(const BF16Vec32&, int)` constructor that doesn't exist on ARM (regression from #39445)
- [Bug]: Deepseek-OCR-2 cannot be deployed on H20 GPUs with vllm[0.20.0] and vllm-docker.
- [Refactor] Nixl util using lazy init
- [Bug]: DSV4 TileLang JIT fails with 'Permission denied: /tmp/tvm-debug-mode-tempdirs/...' on shared multi-user hosts
- [Bug]: TurboQuant fails on non-power-of-2 head_dim (Phi-2, MSE-K presets)
- [Attention][TurboQuant] Sparse V tile-skip (opt-in)
- [XPU] Add INT4 MoE support via INC + vllm-xpu-kernels
- Docs
- Python not yet supported