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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: `BaseThinkingReasoningParser.extract_reasoning` silently discards output text when `<think>` appears mid-stream
- Handle unavailable ROCm GCN architecture fallback
- [ROCm] Fix AITER all-reduce fusion coverage
- [XPU] Work around Battlemage oneCCL IPC handle cache device-loss failures
- Manual silu quant fusion
- [BugFix][Pooling] Skip weight-prefix probe when model has WeightsMapper
- [Bugfix][LoRA] Guard TrtLlm BF16 MoE LoRA gate on activation type
- [Bugfix][R3] Size monolithic routing replay buffer for DP
- [KV Offload] Support out-of-tree secondary tier managers via `module_path`
- [Feature] Enable AITER MXFP4 MoE on gfx942 and optimize tile configurations for MI325X Target Kimi K3 running on MI325X
- Docs
- Python not yet supported