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
- [WIP] [Speculative Decoding] Support draft model on different tensor-parallel size than target model (Extended)
- [Feature]: Supported For Quanto Models
- [Feature]: support logging input and output
- [Bug]: OutOfMemoryError when loading a small model with a huge context length
- [Bug]: server error when hosting TheBloke/Llama-2-7B-Chat-GPTQ with chunked-prefill
- [Misc]: CUDAGraph captured generation stuck with custom_all_reduce and tensor_parallel=2
- [Usage]: About the use of benchmark_latency.py
- [Performance]: Long AllReduce wait time on 1 device with tensor parallelism
- [Bug]: OpenAI API emulation incompatible with shell_gpt OpenAI API calls
- [Bug]: Test_skip_speculation fails in distributed execution
- Docs
- Python not yet supported