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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Fix multiturn think leakage when tool parser is composed with reasoning parser
- [Model] Adding model support for bharatgenai/Param-1-2.9B-Instruct
- Allow skip harmony
- [MM][CG] Support ViT CG for Qwen2-VL
- [Core] Add is_eagle in AttentionSpec
- [Bugfix] Restore moe_forward output shape invariant on TRTLLM MXFP4 path
- Fix KV cache tensor sharing across block sizes
- [Bugfix] Guard against buffered token IDs in BaseThinkingReasoningParser streaming
- Eliminate redundant MoE buffer copies in AITER fused experts (without dependency on AITER changes)
- [kv_offload] Move `FilterReusedOffloadingManager` logic to `CPUOffloadingManager`
- Docs
- Python not yet supported