Files
composable_kernel/example
Jeff Huang 0aa1142bb5 [CK] Add FP8 KV_BLOCKSCALE support for batch prefill
Implement per-page K/V quantization for paged attention:
  - Add KV_BLOCKSCALE enum to BlockAttentionQuantScaleEnum
  - Use exp2 shift trick to eliminate explicit P scaling overhead
  - Prefetch physical pages offset for KV cache, overlaps with computations
2026-02-03 11:18:14 +08:00
..
2026-01-14 07:31:45 -08:00