add llama 3 support to llm.c #1678
ci.yml
on: pull_request
build-cuda-windows
2m 20s
build-ubuntu20-04
2m 50s
build-cuda-fp32
1m 40s
build-cuda-bf16
1m 41s
build-cuda-fp16
1m 28s
build-cuda-kernels
1m 56s
Matrix: build-and-test-cpu