[Bug] recent change of param "block_size_x/y, unroll" in dlight/gpu/matmul.py significantly decrease q4f16_1 prefill speed on android 8gen3 device #39
Triggered via issue
October 30, 2024 06:31
xuguodong1999
Status
Skipped
Total duration
1h 39m 39s
Artifacts
–