sirhcm/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests 2 Actions 8 Activity

lower nv test_gemm_4096 target (#13107)

Browse Source
This commit is contained in:
chenyu
2025-11-05 11:05:16 -05:00
committed by GitHub
parent eff80beeed
commit 18d4ecc1f3
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/external/speed_v_theoretical.py
Vendored
+1 -1
View File
@@ -89,7 +89,7 @@ class TestKernelSpeed(unittest.TestCase):
def test_conv_3x3_256_32_32_256_256(self): self._test_conv_3x3(256, 32, 32, 256, 256, nv_tflops=27, amd_tflops=14)
# theoretical is nv_tflops=165, amd_tflops=123
def test_gemm_4096(self): self._test_matmul(4096, nv_tflops=115, amd_tflops=65)
def test_gemm_4096(self): self._test_matmul(4096, nv_tflops=110, amd_tflops=65)
def test_gemm_8192(self): self._test_matmul(8192, nv_tflops=115, amd_tflops=60)
# theoretical is nv_gbs=1008, amd_gbs=960