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]: Why `use_beam_search` is eliminated in `vllm.SamplingParams` from v0.6.3?
- [Bug]: Authorization ignored when root_path is set
- [Core][Bugfix] Use correct device to initialize GPU data during CUDA-graph-capture
- [Misc]Further reduce BNB static variable
- [Usage]: Use difference SamplingParams for each sample in batch inference via openai api
- [Bug]: Duplicate request_id breaks the engine
- [Performance]: Cannot use FlashAttention-2 backend for Volta and Turing GPUs.
- [Feature][v1]: Add metrics support
- 【Kernel】Tuning fused moe for qwen2-57b in GTX 4090 (tp4pp2)
- [Bug]: Qwen2-VL-7B with sglang (vLLM-back) Performance Degradation on MME benchmark
- Docs
- Python not yet supported