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
- [Bugfix][Mooncake] Make early prefill abort cleanup idempotent
- [Perf][Model Loader] Route sharded_state, reload and Engram table copies through copy_weight_
- [Bugfix][Perf] Cache FABRIC handle fallback in cumem allocator
- [Bugfix][MM] Do not offer cuDNN FP8 ViT attention on SM 12x
- [Bugfix][Attention] Fix V masking for non-causal sliding-window attention
- [Model Loader] streamingly load weights files.
- [Core] Scheduler-owned persistent state for streaming models
- [KV Connector][Mooncake] Fail pulls from a lost prefill worker
- [Bugfix][Tool Parser] llama4_json: parse parallel tool calls without ";" separator
- [Bugfix][Multimodal] Normalize audio layout before resampling
- Docs
- Python not yet supported