Skip to content

Draft: Port three torch2flydsl MoE kernels to FlyDSL 0.2.2 #58

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
irvineoy wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

Draft: Port three torch2flydsl MoE kernels to FlyDSL 0.2.2 #58

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 23 additions & 0 deletions tasks/torch2flydsl/moe_a8w4_kernel/config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
source_file_path:
- kernel.py
target_kernel_functions:
- flydsl_moe_a8w4
- build_moe_stage1_module
- build_moe_stage2_module
- compile_mixed_moe_gemm1
- compile_mixed_moe_gemm2
compile_command:
- python3 -c "import torch; from kernel import build_moe_stage1_module, build_moe_stage2_module;
build_moe_stage1_module(model_dim=7168, inter_dim=256, experts=384, topk=8, tile_m=32,
tile_n=256, tile_k=256, doweight_stage1=False, a_dtype='fp8', b_dtype='fp4', out_dtype='bf16');
build_moe_stage2_module(model_dim=7168, inter_dim=256, experts=384, topk=8, tile_m=32,
tile_n=256, tile_k=256, doweight_stage2=True, a_dtype='fp8', b_dtype='fp4', out_dtype='bf16');
print('compile ok')"
correctness_command:
- python3 test_kernel_harness.py --correctness
performance_command:
- python3 test_kernel_harness.py --full-benchmark
task_type: torch2flydsl
supported_archs:
- gfx950
task_result_template: null
Loading
Loading