OscarXu e7fe8587f6 Add asm for no-loop v3_128x128x128

2025-05-06 10:47:29 +08:00

..

hsa

Add asm for no-loop v3_128x128x128

2025-05-06 10:47:29 +08:00

CMakeLists.txt

Add .co direct asm support by CK_USE_ASM_MOE_STAGE2_BLOCKSCALE

2025-04-30 22:05:54 +08:00

gemm_add_add_xdl_fp16.cpp

[GEMM] gemm_universal related optimization (#1453)

2024-08-14 10:42:30 +08:00

gemm_multiply_multiply_xdl_fp8_ab_scale.cpp

[Block Scale GEMM] Optimized block scale gemm (#1950)

2025-03-11 10:11:21 -07:00

gemm_multiply_multiply_xdl_fp8_bpreshuffle.cpp

[Block Scale GEMM] Optimized block scale gemm (#1950)

2025-03-11 10:11:21 -07:00

gemm_multiply_multiply_xdl_fp8.cpp

Add the instance of MBlock=144 for GemmMultiplyMultiply (#1955)

2025-03-07 13:44:06 -08:00

gemm_multiply_multiply_xdl_int8.cpp

[A8W8 GEMM] Optimized weight-preshuffled implementation & add quantization datatype for CK TILE rms_norm (#1862)

2025-02-20 14:00:27 -08:00

moe_gemm1_xdl_fp8.cpp

ck moe gemm implement (#1936)

2025-03-05 15:56:55 +08:00

moe_gemm1_xdl_pk_i4.cpp

ckmoe: change cmake; use smaller shape for i4 (#2027)

2025-03-27 09:04:31 -07:00

moe_gemm2_xdl_fp8_blockscale.cpp

Fix int overflow casued by large B matrix

2025-04-28 15:55:10 +08:00

moe_gemm2_xdl_fp8.cpp

Ck int4 moe develop (#1949)

2025-03-10 11:16:44 +08:00

moe_gemm2_xdl_pk_i4.cpp

ckmoe: change cmake; use smaller shape for i4 (#2027)

2025-03-27 09:04:31 -07:00