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

..

ck

Fix one more lifetimebound error. (#3703)

2026-02-02 18:25:56 -08:00

ck_tile

[CK] Add FP8 KV_BLOCKSCALE support for batch prefill

2026-02-03 11:18:14 +08:00

rapidjson

Update pre-commit to fixed versions, run remod for ck_tile (#2895)

2025-10-16 15:29:17 -07:00