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
- [Spec Decode] Lazy recovery in rejection sampling: compute recovered tokens in-kernel on first rejection
- Add opt-in FP8 vocab embedding support
- [Usage]: Is there someway to accelerate deepseek v4 flash/pro load ckpt time?
- [Bug]:[Qwen3.5] V1 KV cache page size unification fails for Qwen3.5/Qwen3.6 hybrid GPTQ Marlin model
- [ROCm][AITER] Enable shuffled rope and KV-cache fusion
- [Bugfix][MLA][DCP] Round chunked-prefill workspace and max_context_chunk to satisfy DCP divisibility asserts
- [Docs] Document NIXL KV connector metrics aggregation semantics
- Allow non-3 number of target hidden layers for Eagle-3 models
- [ROCm] AITER config object
- [Bugfix] [Weight Loader] Add Fp8OnlineLinearMethod to WEIGHT_LOADER_V2_SUPPORTED
- Docs
- Python not yet supported