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]: Chunked prefill vs. non-chunked output is different for a long prompt
- [Bug]: Illegal memory access for MoE kernel with large workloads
- [Bug]: qwen1.5-32b-chat no response
- [Hardware][Intel CPU]use ipex varlen attention to compute prompts for better performance.
- [PoC][Spec Decoding] Stop speculating when confidence is low
- [Bug]: The end_sync operation inside the cross_device_reduce_2stage kernel sometimes deadlocks because it can't wait for the end signal.
- feat: controlling max queue time
- [Installation]: Wrong torch header file referenced when compiling from source
- [Feature]: Add distributed inference support for lora adapters.
- [Bug]: TRACKING ISSUE: `AsyncEngineDeadError`
- Docs
- Python not yet supported