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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Graph Capturing reports negative memory consumption
- Add support to pass custom presence_penalty and frequency_penalty parameters in the generation config
- [New Model]: MetaCLIP-2 variants
- [Core] Add sharding metadata to model parameters
- [Bug]: invoke_fused_moe_wna16_*_kernel calls get_moe_wna16_block_config with bad parameters
- [Bugfix][NIXL] Compute NIXL throughput using timestamps instead of summed durations
- [Bugfix] Fix LoRA + TP > 1 crash due to non-contiguous input tensor in lora_shrink_op.py
- [XPU][QWEN3_NEXT] remove fla hardcode to cuda
- [RFC]: Model-specific realtime streaming abstraction
- [Bugfix] Fix MiniMax M2 TP dimension issue in q_norm and k_norm
- Docs
- Python not yet supported