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
- [Bugfix] Cover uniform decode sizes under an explicit max_cudagraph_capture_size
- [ROCm] Add V1 streamed BF16 pipeline transport
- [Qwen4Exp][ROCm] Support FP8 PLE n-gram checkpoints on the AMD path
- [Bug]: encoder attention rejects quantized KV cache only at request time
- [Bug]: prefix caching and KV-scale calculation assert on encoder models
- [Bug]: encoder prompt embeddings trigger a compiled AttributeError
- [Bugfix][KV Connector][ROCm] Fix MoRI-IO KV block-offset for speculative decoding (MTP)
- [Attention] Add FlashInfer SM120 FP8 PRIMS prefill
- [Bug]: step3 streaming tool parser returns empty arguments unless each token arrives in its own delta
- [Bugfix][KV Connector][Mooncake] Drop NULL_BLOCK_ID pairs after P/D block alignment
- Docs
- Python not yet supported