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 supported2 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: fp8 performance is worse than fp16 when batch size is 1
- [Feature]: Benchmark script with speculative decode metrics
- [Feature]: Context Parallelism
- [Usage]: vllm流式输出会出现卡顿的现象,会卡6-9秒,是什么原因导致的,输入长度4万多字
- [WIP] Store speculative states
- [Bug]: CTRL+C Not Killing Process with distributed_executor_backend=mp in VLLM v0.5.3.post1
- [Usage]: Extremely slow inference with Llama 3.1 70b Instruct
- [Installation]: vllm install error in jetson agx orin
- [Kernel][LoRA] Add assertion for punica sgmv kernels
- [Bug]: vllm serve downloads both consolidated.safetensors and shared safetensors, when it should only download one of them.
- Docs
- Python not yet supported