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
- [Quantization] Implement FP8 block padding for unaligned cases
- [Bugfix][MRV2] Respect dynamic K=0 from scheduler in AutoRegressiveSpeculator
- [KV Offload] Add TieringAdmissionPolicy skeleton (factory/base/always)
- [Frontend] [Parser] Migrate llama3_json/llama4_json to the streaming parser engine
- [Perf] Add adaptive sync-less DeepEP v2 prefill dispatch
- [Memory] Measure complete CUDA graph capture footprint for KV budgeting
- docs: clarify Metal quickstart model choice
- [KVConnector] Count async loads per request in MultiConnector
- [LoRA] Fix lm_head delta silently dropped from prompt_logprobs (#51594)
- [XPU][MoE] Resize batched Triton MoE tiles and change grid order
- Docs
- Python not yet supported