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
- [Misc] Delay EPLB Nixl import until needed
- [ROCm][DSv4] implement flash sparse mla with triton kernels
- [Responses API] Fold developer-role input messages into instructions
- [Perf] Replace cudaMemsetAsync with in-kernel cleanup for persistent_topk
- Add opt-in Unicode tag-block sanitization middleware
- Fix EP precision for Qwen3 MoE shared expert under sequence-parallel MoE
- fix(spec-decode): resync thinking state before target logits in rejec…
- [Kernel] Fuse logit softcapping into a single Triton kernel
- [Bug]: gemma4 31B MTP Avg Draft acceptance rate: 0.2%
- [Bugfix][Model] Fix DeepSeek V4 scale_fmt default for non-canonical quant configs
- Docs
- Python not yet supported