NV tensor_cores in kernel.py (#4399)

This commit is contained in:
chenyu
2024-05-02 22:33:08 -04:00
committed by GitHub
parent 0deaaf2bc8
commit d4062cb6fc
2 changed files with 4 additions and 0 deletions

View File

@@ -123,6 +123,8 @@ jobs:
CUDA=1 BFLOAT16=1 DEBUG=2 python3 extra/gemm/simple_matmul.py | tee matmul_bfloat16.txt
- name: Run Tensor Core GEMM (PTX)
run: CUDA=1 PTX=1 HALF=1 DEBUG=2 python3 extra/gemm/simple_matmul.py | tee matmul_ptx.txt
- name: Run Tensor Core GEMM (NV)
run: NV=1 HALF=1 DEBUG=2 python3 extra/gemm/simple_matmul.py | tee matmul_nv.txt
- name: Fuzz Padded Tensor Core GEMM(CUDA)
run: CUDA=1 M_START=12 M_STOP=20 M_STEP=1 N_START=6 N_STOP=10 N_STEP=1 K_START=28 K_STOP=36 K_STEP=1 HALF=1 TC_OPT=2 python3 ./extra/gemm/fuzz_matmul.py
- name: Fuzz Padded Tensor Core GEMM(PTX)
@@ -160,6 +162,7 @@ jobs:
matmul.txt
matmul_bfloat16.txt
matmul_ptx.txt
matmul_nv.txt
llama_unjitted.txt
llama_jitted.txt
llama_beam.txt