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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ROCm][Perf][DSv4.1] Shard the sparse-indexer decode rows across TP
- [Bugfix][Core] Reject negative block counts in the free-block pool APIs
- [Model] Enable audio-conditioned hidden-state extraction for Ming ASR
- [ROCm][Muse Spark] DSpark Markov sampling with one launch a round (--monokernel)
- [Bugfix][DSA] Stage ShardQ indexer indices in fresh host memory each step
- [Perf][MiniMax-M3] Shard large batches by token and fuse the MoE finalize into the reduce-scatter
- [Bug]: thinking_token_budget turns off reasoning when an earlier message mentions <think>
- [Bugfix][Reasoning] Don't count a start marker quoted in an earlier message against thinking_token_budget
- [Fast start] Support D2D scaling for multi-node serving
- [RL][Model Loader] Load plan: per-family plan == load_weights tests
- Docs
- Python not yet supported