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 supported3 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: TRACKING ISSUE: `AsyncEngineDeadError`
- [Bug]: TRACKING ISSUE: CUDA OOM with Logprobs
- [Bug]: Inconsistent Responses with VLLM When Batch Size > 1 even temperature = 0
- [WIP] [Speculative Decoding] Support draft model on different tensor-parallel size than target model (Extended)
- [Bug]: Test_skip_speculation fails in distributed execution
- [Model] Initialize deepseek-vl support
- [Bug]: 使用vllm+ray分布式推理报错
- [RFC]: Support sparse KV cache framework
- [Bug]: VLLM usage on AWS Inferentia instances
- [Bug]: "Triton Error [CUDA]: device kernel image is invalid" when loading Mixtral-8x7B-Instruct-v0.1 in fused_moe.py
- Docs
- Python not yet supported