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
- add `TypeLogitsProcessor`
- [Misc] Added devcontainer to help vscode dev setup
- [Feature]: Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference
- [Bug]: When enforce_eager is True or False, the paged_attention version used is inconsistent
- [Usage]: prompt_logprompt from endpoint
- [Performance]: Why the avg. througput generation is low?
- [Feature]: Support W4A8KV4 Quantization(QServe/QoQ)
- [Feature]: Host CPU Docker image on Docker Hub
- [Bug]: multi-gpu for baichuan2-13B-Chat benchmark_serving
- [Performance]: Will memcpy happen with distributed kv caches while decoding ?
- Docs
- Python not yet supported