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]: Using tensor-parallel-size 4 fails for some models with pyo3_runtime.PanicException: The global thread pool has not been initialized.: ThreadPoolBuildError {"Resource temporarily unavailable" })
- [RFC]: Implement disaggregated prefilling via KV cache transfer
- [RFC]: Branch based version control, and development version
- [Usage]: how to use marlin kernel for GPTQ model
- [Performance]:
- [Bug]: RuntimeError: CUDA error: no kernel image is available for execution on the device
- [CI/Build] Each PR only uses 1 Machine (AMD)
- [Bug]: OOM when setting prompt_logprobs=1
- [RFC]: Usage Data Enhancement for v0.5.*
- [Performance]: How use vllm.attention.ops.triton_flash_attention replace flash_attn package
- Docs
- Python not yet supported