mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 13:11:25 +00:00
4d041837ad
* Adding RapidJson Library * Adding Json Dumps in all CK_Tile Examples Not verified yet * Adding json to cktile Batched Transpose * adding json dumps to layernorm2d_fwd * Adding json dump to flatmm_basic * Adding RapidJson Library * Adding Json Dumps in all CK_Tile Examples Not verified yet * Adding json to cktile Batched Transpose * adding json dumps to layernorm2d_fwd * Adding json dump to flatmm_basic * Adding json in 03_gemm * Add json dump to 16_batched_gemm * Add json dump to gemm_multi_d_fp16 * Add json dump to grouped_gemm * fix fmha_bwd/fwd * Fix clang-format errors exclude include/rapidjson in jenkins as its a third-party library * Saparating function and defination. * Update Documentation of 03_gemm * Refactoring as per code review * Disable fp8 instances on unsupported targets (#2592) * Restrict building of gemm_universal_preshuffle_f8 instances to specific targets in CMakeLists.txt * Add condition to skip gemm_xdl_universal_preshuffle_f8 instances for unsupported targets in CMakeLists.txt * Add conditions to skip unsupported targets for gemm_universal_preshuffle_f8 and gemm_xdl_universal_preshuffle_f8 instances in CMakeLists.txt * Refine conditions to exclude gemm_universal_preshuffle_f8 instances for unsupported targets in CMakeLists.txt --------- Co-authored-by: AviralGoelAMD <aviralgoel@amd.com> * fix clang format * remove duplicate lines of code from library/src/tensor_operation_instance/gpu/CMakeLists.txt * Fixing Readme and unifying jsondumps * adding moe_smoothquant * adding fused_moe * Fixing Readme for batched_gemm * Fixing Readme for grouped_gemm * adding flatmm * adding gemm_multi_d_fp16 * adding elementwise * adding File name when json is dumped * Fixing Reduce after merge * adding batched_transpose * Adding Warptile in Gemm * Fixing Clang Format --------- Co-authored-by: Aviral Goel <aviral.goel@amd.com> Co-authored-by: AviralGoelAMD <aviralgoel@amd.com> Co-authored-by: illsilin_amdeng <Illia.Silin@amd.com>
1.3 KiB
1.3 KiB
moe-smoothquant
This folder contains example for moe-smoothquant using ck_tile tile-programming implementation.
Unlike standard smoothquant op, the input scale is from different expert [expert, hidden], we need reuse the topk-id from previous topk-softmax and select the corresponding expert from current topk, and expand the output/per-token-scale by topk
build
# in the root of ck_tile
mkdir build && cd build
sh ../script/cmake-ck-dev.sh ../ <arch> # you can replace this <arch> to gfx90a, gfx942...
make tile_example_moe_smoothquant -j`nproc`
This will result in an executable build/bin/tile_example_moe_smoothquant
example
args:
-t tokens dimension (default:3328)
-h hidden_size dimension (default:4096)
-e experts (default:32)
-k topk (default:5)
-stride stride per row, if -1 then equal to hidden_size (default:-1)
-v cpu validation or not (default:1)
-kname print kernel name or not (default:1)
-prec_i input precision, fp16/bf16 (default:fp16)
-prec_o precision, int8/fp8 (default:int8)
-warmup cold iter (default:5)
-repeat hot iter (default:20)
-json 0: No Json, 1: Dump Results in Json format (default:0)
-jsonfile json file name to dump results (default:moe_smoothquant.json)