Skip to content

Fix MOE layer sync test #936

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

Merged
kevalmorabia97 merged 1 commit into from
Feb 26, 2026
Merged

Fix MOE layer sync test #936

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
6 changes: 6 additions & 0 deletions tests/gpu_megatron/torch/quantization/plugins/test_megatron.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -765,6 +765,12 @@ def _test_layer_sync_moe_local_experts_amax(ep_size, moe_grouped_gemm, rank, siz
num_moe_experts=8,
transformer_impl="modelopt",
)
# Make weight initialization different across experts, otherwise experts will have similar amax values
for layer in model.decoder.layers:
for i, expert in enumerate(layer.mlp.experts.local_experts):
expert.linear_fc1.weight.data.fill_(0.1 + i * 0.05)
expert.linear_fc2.weight.data.fill_(0.2 + i * 0.05)

quant_cfg = mtq.FP8_DEFAULT_CFG
model = mtq.quantize(model, quant_cfg, get_forward(model))

Expand Down