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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Run Cohere2MoE shared experts outside FusedMoE for better prefill TTFT.
- [Feature]: Anthropic messages search_result content block support
- [Bugfix][V1] Warm up all top-k/top-p Triton sampler kernel specializations
- [Bugfix][Reasoning] Mistral: fix [THINK]/[/THINK] leaking into content when emitted as plain text in streaming
- [Bugfix][Core] Fix Mamba prefix cache EAGLE hit
- VLLM Support Container Snapshot on NPU
- [Feat] Add request arrival and completed log
- Enable return_routed_experts support with CPU KV offload
- [Bugfix] Fix token splitting caused by stop string truncation in the incremental detokenizer
- fix(v1/engine): report pid + exit signal when a core proc dies during init
- Docs
- Python not yet supported