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
- Does 'all-reduce kernels are temporarily disabled' is the cause for the more memory requirment?
- [TEST] Add a distributed test for async LLM engine.
- (core dumped) when running `vllm` with `AWQ` on `MIG` partition of a H100 GPU
- [Feature] Implement FastV's Token Pruning
- [Bug]: RuntimeError: invalid argument to reset_peak_memory_stats when offline sampling using neuron
- [Test] Add a randomized test for OpenAI API
- [New Model]: LoRA for Deepseek-coder-7b-instruct is not supported due to vocab size limit
- [Bug]: ValueError: Asking to pad but the tokenizer does not have a padding token. Please select a token to use as `pad_token` `(tokenizer.pad_token = tokenizer.eos_token e.g.)` or add a new pad token via `tokenizer.add_special_tokens({'pad_token': '[PAD]'})`
- [Bug]: Under the beam search setting, the output is abnormal
- [Usage]: Using a base model with a LoRA on top with AsyncLLMEngine for token streaming
- Docs
- Python not yet supported