Update LLM Perf Benchmarks - CUDA PyTorch #89
update_llm_perf_cuda_pytorch.yaml
on: workflow_dispatch
Matrix: run_benchmarks
Annotations
2 errors
run_benchmarks (gptq, 1xT4, aws-g4dn-2xlarge)
The run was canceled by @baptistecolle.
|
run_benchmarks (gptq, 1xT4, aws-g4dn-2xlarge)
The operation was canceled.
|