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
- Beam Search Length Normalization Wrong
- KeyError: 'base_model.model.lm_head.base_layer.weight'
- Watchdog caught collective operation timeout for llama2-70b-chat on tp=8
- Llama Guard inconsistent output between HuggingFace's Transformers and vLLM
- support set logprobs to model vocab size
- Controlling max queue time
- Speculative Streaming: Fast LLM Inference without Auxiliary Models
- 求问 qwen-14b微调后的模型用vllm推理后结果都为空
- [BUG] Prompt logprobs causing tensor broadcast issue in `sampler.py`
- Fatal Python error: Segmentation fault
- Docs
- Python not yet supported