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
- [RFC][ROCm]: Decode Context Parallelism (DCP) for DeepSeek-V4 hybrid SWA + compressed KV cache
- [Perf][TP] Skip full-vocabulary gather for exact greedy sampling
- [WIP][Model][ROCm][DCP] DeepSeek-V4 decode context parallelism
- [Bugfix][Parser] Resolve stripped special-token terminals without holding the stream
- [Bug]: nvidia/audio-flamingo-next-hf fails to load — get_audio_features() missing required argument 'input_ids'
- [Bugfix][Mamba] Keep the mamba block size a multiple of the chunk size
- [KVConnector] Classify transfer groups from the framework's spec kinds
- [Kernel][GDN] Use flashinfer bf16 mm for the GDN gate projection
- [Feature][KV Offload] Support joint GPU/CPU prefix cache lookup
- [V1][Perf] Cap detokenizer prompt-prime window for long prompts
- Docs
- Python not yet supported