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
- [RFC]: Asymmetric P/D Deployment for DeepSeek-V4.1 Flash
- [Model] Add BerryLM (hybrid KDA / full attention MoE with Gated Block AttnRes)
- [Model] Use upstream GLM-5.3 and Qwen4-Exp configs and processor
- [Bugfix][MLA] Fix SM120 sparse-MLA prefill IMA with DSpark speculative decoding (#56771)
- [MRV2] Keep warmup out of the EPLB load stats
- [ROCm][DSv4.1][Perf] One-pass dequantize and a gather-sized grid for the compressed K cache
- [Bugfix][XPU] Select graph capture profiler activity from runner device
- [Bug] Greedy LoRA decode nondeterministic on Qwen3.8-27B-FP8 (rank-64 Unsloth, linear_attn modules)
- [Attention] Allow explicit FlashInfer CuTe DSL MLA decode selection
- [Bug]: Startup memory-profiling assertion aborts whenever free memory grows, contradicting documented support for GPU co-tenancy
- Docs
- Python not yet supported