mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-02 20:51:23 +00:00
Support fp8 dynamic quantization for fmha (#3206)
* Support qscale for dynamic quant, remove static quant * Support hdim=256 * Remove bias test case for fp8 --------- Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com> Co-authored-by: asleepzzz <hanwen.chang@amd.com>
This commit is contained in:
@@ -4,6 +4,7 @@
|
||||
#pragma once
|
||||
|
||||
#include "ck_tile/ops/fmha/block/block_attention_bias_enum.hpp"
|
||||
#include "ck_tile/ops/fmha/block/block_attention_quant_scale_enum.hpp"
|
||||
#include "ck_tile/ops/fmha/block/block_dropout.hpp"
|
||||
#include "ck_tile/ops/fmha/block/block_masking.hpp"
|
||||
#include "ck_tile/ops/fmha/block/block_position_encoding.hpp"
|
||||
|
||||
Reference in New Issue
Block a user