add llama 3 support to llm.c #1650
ci.yml
on: pull_request
build-cuda-windows
1m 27s
build-ubuntu20-04
2m 45s
build-cuda-fp32
1m 22s
build-cuda-bf16
1m 16s
build-cuda-fp16
1m 16s
build-cuda-kernels
1m 41s
Matrix: build-and-test-cpu