ltqin 67f0b74ec6 Revert "Revert " Fp8 block scale quantization for fmha fwd (#3330)" (#3633)" (#3635) ...

This reverts commit de5a1d730d.

Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>

2026-01-23 09:03:22 -08:00

..

block_attention_bias_enum.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

block_attention_kvcache_layout_enum.hpp

[FMHA] Batch Prefill Support Improvements: Change KV Cache Layout & Large Page Size Support (#3442)

2026-01-05 18:41:47 +08:00

block_attention_quant_scale_enum.hpp

Revert "Revert " Fp8 block scale quantization for fmha fwd (#3330)" (#3633)" (#3635)

2026-01-23 09:03:22 -08:00

block_dropout.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

block_masking.hpp

Add attention sink support for FMHA FWD (#3368)

2025-12-15 12:21:59 +08:00

block_position_encoding.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

block_rotary_embedding.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

page_block_navigator.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

variants.hpp

Add attention sink support for FMHA FWD (#3368)

2025-12-15 12:21:59 +08:00