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
- [New Model]: FM9GForCausalLM
- [Model] LoRA with lm_head and embed_tokens fully trained
- [Bug]: when tensor-parallel-size>1,Stuck
- [Usage]: Using TPU example with InternVL2 Model
- [Bug]: TPU InternVL2 Model Error Graph break due to unsupported builtin _XLAC.PyCapsule._xla_get_replication_devices_count
- [Bug]: Inconsistent generation with guided_json, speculative decoding and temp > 0.0
- [Feature]: Contribute T5 model to vLLM
- [Performance]: Sampler is too slow?
- [Hardware][Ascend] Add Ascend NPU backend
- [Performance]: Issues with prefix cache usage
- Docs
- Python not yet supported