huggingface/optimum-benchmark Issues
Training benchmarks reproduction
Updated 3vllm backend uses too much vram
Closed 4hangs,can not continue.
Closed 12Onnxruntime Seq2Seq doesn't work
Closed 3More tests
Closed 9regression testing api
UpdatedWarning on loading quantized model
Updated 1Moving model to one device
Closed 5Trt llm surport question
Closed 9How can I test my local model?
Closed 1Remove `cuda` synchronizations
Closed 1Timm support
ClosedTP and DP support for inference
Closed 1TGI support
ClosedSimulate GPTQ quantization
Closed 3