msaffari-amd
ee3ada6e4a
[AITERKER-112] PER_TOKEN_HEAD: support page_size < kN0 via cross-page dequant
...
- Pipeline: remove kPageBlockSize >= kN0 static_assert; QK dequant now
precomputes tile_k_pages[] and indexes per-column. page_size >= kN0 stays
on the original single-page fast path (kPagesPerTile==1).
- Codegen: add page_size=64 to SUPPORTED_PAGE_SIZE; drop per_token_head from
the page_size < tile.F_bn0 filter (kv_blockscale still filtered).
2026-05-20 14:21:12 +00:00
..
2026-01-26 12:57:09 -08:00
2026-01-07 16:30:57 +01:00
2025-11-28 13:49:54 -08:00
2025-11-28 13:49:54 -08:00
2025-12-18 07:59:45 +01:00
2025-11-28 13:49:54 -08:00
2025-10-16 03:10:57 -07:00
2026-03-06 16:28:22 +00:00
2026-01-07 16:30:57 +01:00
2026-03-12 08:48:36 +00:00
2026-02-26 00:28:58 +00:00
2026-03-12 08:48:36 +00:00
2025-12-18 07:59:45 +01:00
2025-11-28 13:49:54 -08:00
2025-11-28 13:49:54 -08:00
2026-02-25 20:11:01 +00:00
2025-11-28 13:49:54 -08:00
2026-01-07 16:30:57 +01:00
2026-01-07 16:30:57 +01:00
2026-01-07 16:30:57 +01:00
2026-01-17 08:30:27 +01:00
2026-04-11 10:01:30 +00:00
2025-11-28 13:49:54 -08:00
2025-11-28 13:49:54 -08:00
2026-01-17 08:30:27 +01:00
2026-01-07 16:30:57 +01:00
2025-11-28 13:49:54 -08:00
2025-11-28 13:49:54 -08:00
2026-01-07 16:30:57 +01:00
2025-11-28 13:49:54 -08:00
2026-02-20 22:41:34 +00:00
2026-01-07 16:30:57 +01:00
2026-01-20 13:06:59 -08:00
2025-12-30 16:25:08 +01:00
2025-11-28 13:49:54 -08:00
2026-05-08 14:15:31 +00:00
2025-11-28 13:49:54 -08:00
2026-01-07 16:30:57 +01:00
2025-11-28 13:49:54 -08:00
2026-01-07 16:30:57 +01:00
2026-01-07 16:30:57 +01:00
2025-11-28 13:49:54 -08:00
2025-11-28 13:49:54 -08:00
2025-11-28 13:49:54 -08:00
2025-11-28 13:49:54 -08:00
2025-11-28 13:49:54 -08:00
2025-11-28 13:49:54 -08:00
2025-11-28 13:49:54 -08:00
2025-11-28 13:49:54 -08:00
2025-11-28 13:49:54 -08:00
2026-02-25 05:17:08 +00:00
2026-04-10 15:18:02 +00:00
2025-11-28 13:49:54 -08:00
2026-01-30 17:02:14 +01:00
2025-11-28 13:49:54 -08:00
2025-11-28 13:49:54 -08:00
2026-04-10 15:18:02 +00:00
2026-04-11 10:01:30 +00:00
2026-01-07 16:30:57 +01:00
2026-01-15 16:43:02 +01:00
2026-01-15 16:43:02 +01:00
2026-05-20 14:21:12 +00:00
2026-01-14 07:31:45 -08:00
2024-12-04 00:46:47 +01:00