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 supported4 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Unable to use fp8 kv cache with chunked prefill on ampere
- [Model] 1.58bits BitNet Model Support
- [Multi-step] Remove redundant CPU to GPU transfer for non-last rank PP/TP
- [Bug]: Using CPU for inference, an error occurred. [Engine iteration timed out. This should never happen! ]
- [Bug]: when using llama-3.1-70b-instruct for inference, input with large number of tokens(>8k) will result in endless output
- [RFC]: Add Ascend NPU as a new backend
- [Kernel] Add opcheck tests for punica kernels
- [Misc] Allow for unsigned zero NAN representation in ScalarType
- [WIP][Model][Kernel][Bugfix] Commits for new MSFT PhiMoE model
- [Kernel] Support prefill and decode attention kernel in parallel
- Docs
- Python not yet supported