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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Performance]: ROPE + KV-Cache-Write + pre-attn prepare-ops fusion
- [Usage]: multi-gpu,I want embedding model deploy on GPU1, and set CUDA_VISIBLE_DEVICES=1, in vllm start script file, but vllm service still malloc memory of GPU 0 。
- feat: enable vLLM inference for pruned Qwen2 models
- [Attention] remove decode wrapper of flashinfer
- [Usage]: Apertus --tool-call-parser value
- [Bug]: type object 'GroupShape' has no attribute '__origin__' when trying to use with torch.compile
- [Bug]: TritonAttn Backend is very slow on A770
- [New Model]: Issac 0.1
- [Core] Support openai HarmonyContext plugin
- [Bug]: NCCL OOM at 1k concurrency using default memory for DP=16 decode with EPLB and 16 redundant experts
- Docs
- Python not yet supported