ViperEkura cb51a3587b perf: optimize fused FP8 GEMM kernel

2026-08-18 19:56:15 +08:00

..

attn_paged_test.cu

perf: precompute ragged Q tile scheduling

2026-08-16 23:32:46 +08:00

attn_test.cu

perf: optimize small-head causal prefill

2026-08-14 23:25:49 +08:00

fp8_mma_test.cu

perf: optimize fused FP8 GEMM kernel

2026-08-18 19:56:15 +08:00

test_utils.cuh

refactor: unify attention param field names

2026-08-09 20:23:58 +08:00