add llama 3 support to llm.c #1681
ci.yml
on: pull_request
build-cuda-windows
2m 9s
build-ubuntu20-04
2m 41s
build-cuda-fp32
1m 23s
build-cuda-bf16
1m 18s
build-cuda-fp16
1m 19s
build-cuda-kernels
1m 29s
Matrix: build-and-test-cpu