mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-02 12:41:26 +00:00
Dev/a8w4 and a8w8splitk (#3447)
* Ck moe bs splitk pr (#3440) * splitk kick-off. Compilation fail * splitk hack pass * fix scale offset calc. * clang-format for a8w8_moe_blk_gemm1 splitk change * fix testcase error --------- Co-authored-by: oscar <huaiguxu@amd.com> Co-authored-by: huaiguxu <145733371+huaiguxu@users.noreply.github.com> * Zan/moe a8w4 (#3441) * update * update * update ck moe a8w4 * update * update * update * compile pass * update * update * python3 op_tests/test_moe_2stage.py -t 16 -e 1 -k 1 -dim 256,256 ready * support new a8w4 kernel * update * update ck_tile * re format * update * update * fix conflict * fix build * update ck_tile moe * fix clang format * fix the problem * fix accruacy issue * fix --------- Co-authored-by: oscar <huaiguxu@amd.com> Co-authored-by: huaiguxu <145733371+huaiguxu@users.noreply.github.com> Co-authored-by: Zzz9990 <zanzhang@amd.com> Co-authored-by: felix <felix.li@amd.com>
This commit is contained in:
@@ -309,25 +309,6 @@ using WarpGemmMfma_f32_16x16x64_bf8_bf8 = WarpGemmImpl<WarpGemmAttributeMfmaIter
|
||||
template <typename A, typename B, WGAttrNumAccessEnum AttrNumAccess = WGAttrNumAccessEnum::Single>
|
||||
using WarpGemmMfma_f32_16x16x128_f8f6f4 = WarpGemmImpl<
|
||||
WarpGemmAttributeMfma<WarpGemmAttributeMfmaImpl_f32_16x16x128_f8f6f4<A, B>, AttrNumAccess>>;
|
||||
template <WGAttrNumAccessEnum AttrNumAccess = WGAttrNumAccessEnum::Single>
|
||||
using WarpGemmMfma_f32_16x16x128_fp8_fp8 = WarpGemmImpl< //
|
||||
WarpGemmAttributeMfma<WarpGemmAttributeMfmaImpl_f32_16x16x128_f8f6f4<fp8_t, fp8_t>,
|
||||
AttrNumAccess>>;
|
||||
|
||||
template <WGAttrNumAccessEnum AttrNumAccess = WGAttrNumAccessEnum::Single>
|
||||
using WarpGemmMfma_f32_16x16x128_fp8_bf8 = WarpGemmImpl< //
|
||||
WarpGemmAttributeMfma<WarpGemmAttributeMfmaImpl_f32_16x16x128_f8f6f4<fp8_t, bf8_t>,
|
||||
AttrNumAccess>>;
|
||||
|
||||
template <WGAttrNumAccessEnum AttrNumAccess = WGAttrNumAccessEnum::Single>
|
||||
using WarpGemmMfma_f32_16x16x128_bf8_fp8 = WarpGemmImpl< //
|
||||
WarpGemmAttributeMfma<WarpGemmAttributeMfmaImpl_f32_16x16x128_f8f6f4<bf8_t, fp8_t>,
|
||||
AttrNumAccess>>;
|
||||
|
||||
template <WGAttrNumAccessEnum AttrNumAccess = WGAttrNumAccessEnum::Single>
|
||||
using WarpGemmMfma_f32_16x16x128_bf8_bf8 = WarpGemmImpl< //
|
||||
WarpGemmAttributeMfma<WarpGemmAttributeMfmaImpl_f32_16x16x128_f8f6f4<bf8_t, bf8_t>,
|
||||
AttrNumAccess>>;
|
||||
|
||||
template <WGAttrNumAccessEnum AttrNumAccess = WGAttrNumAccessEnum::Single>
|
||||
using WarpGemmMfma_f32_16x16x128_fp8_fp8_CTransposed =
|
||||
|
||||
Reference in New Issue
Block a user