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
- [Feature]: Return hidden states (in progress?)
- [Bug]: As V100 does not support FlashAttention, it is not possible to run the gemma model, hopefully it can support the xformers way to run it
- [Feature]: ROPE scaling supported by vLLM gemma2
- [Bug]: Batch expansion doesn't work with lora
- [Bug]: When running gemma2 7b, an error is reported [rank0]: RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling `cublasGemmEx( handle, opa, opb, m, n, k, &falpha, a, CUDA_R_16BF, lda, b, CUDA_R_16BF, ldb, &fbeta, c, CUDA_R_16BF, ldc, compute_type, CUBLAS_GEMM_DEFAULT_TENSOR_OP)` Set up according to the prompts: os.environ['VLLM_ATTENTION_BACKEND'] = 'FLASHINFER' print("Environment variable set for VLLM_ATTENTION_BACKEND:", os.getenv('VLLM_ATTENTION_BACKEND'))
- [Bug]: CUDA error when using multiple GPUs
- [Feature]: Model ChatGLMForCausalLM does not support LoRA, but LoRA is enabled.
- [Performance]: the performance with chunked-prefill-enabled is lower than default
- 加载Baichuan2-13B-Chat时出异常,torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 50.00 MiB. GPU
- [Feature]: expose the tqdm progress bar to enable logging the progress
- Docs
- Python not yet supported