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
- [Usage]: Is there still room to improve the first frame response speed TTFT
- [Bug]: Error in benchmark model with vllm backend for endpoint /v1/chat/completions
- [Usage]: Sending in pre-tokenized question during inference doesn't seem any faster than raw text.
- [Feature]: Enhance integration with advanced LB/gateways with better load/cost reporting and LoRA management
- [Bug]: Requests aren't aborted when client disconnects if user provided a middleware
- [Feature]: Support for priority preemption with chunked-prefill
- [Usage]: [XPU] offline_inference.py - RuntimeError: oneCCL: exec.cpp:122 start_workers: EXCEPTION: failed to start worker # 0
- [RFC]: Merge input processor and input mapper for multi-modal models
- [Core/Bugfix] Per FlashInfer API changing data_type to kv_data_type for kv_cache
- [Bug]: fixie-ai/ultravox-v0_4 throws Out of Memory
- Docs
- Python not yet supported