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 supported4 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: When use `guided choice` feature, vllm.engine.async_llm_engine.AsyncEngineDeadError
- [Bug]: ValueError: Queue <multiprocessing.queues.Queue object at 0x7f5703d2d0f0> is closed;zipfile.BadZipFile: Bad magic number for file header
- [Usage]: Can vLLM handle multi-turn and multi-instance at the same time?
- [Bug]: Mismatch in TTFT count and number of successful requests completed
- [Bug]: vLLM 0.5.5 and FlashInfer0.1.6
- [Performance]: Too slow when serving for large number of prompts.
- [Bug]: Persistent OutOfMemoryError error when using speculative decoding
- [Feature]: Support multi-node serving on Kubernetes
- [Performance]: TTFT increases linearly with the number of batched tokens
- [Model] LoRA with lm_head and embed_tokens fully trained
- Docs
- Python not yet supported