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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- fix: Correct reasoning-end detection for prompt history
- [MegaMoE] Support external DP load balancing with DeepGEMM MegaMoE
- [MoE Refactor] Combine CompressedTensorsWNA16MarlinMoEMethod with CompressedTensorsWNA16MoEMethod
- [Feature] KVarN: Variance-Normalized KV-Cache Quantization (4-bit K, 2-bit V)
- [KV Cache Quantization] SQuat: Subspace-orthogonal KV Cache Quantization
- [Usage]: Claude code does not work with vLLM
- Add global cache scope for ngram prompt lookup
- Move DP sync to a dedicated CUDA stream
- [Triton][Spec Decode] Non-causal support + relax 3D-launch gate for multi-query verify in unified attention
- [Bugfix][Quantization] Fp8 family: match modules_to_not_convert by substring
- Docs
- Python not yet supported