Skip to content

Fix TEGroupedLinear quantization for expert parallelism (EP > 1) #833

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
yueshen2016 merged 1 commit into from
Feb 6, 2026
Merged

Fix TEGroupedLinear quantization for expert parallelism (EP > 1) #833

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
12 changes: 11 additions & 1 deletion modelopt/torch/quantization/plugins/transformer_engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,7 +156,17 @@ def te_grouped_quantized_linear_fn(package, func_name, self, *args):
_assert_te_fp8_enabled()
idx = 1 if func_name == "_forward" else 0
inp = args[idx]
num_gemms = len(args[idx + 1])

# Handle both old and new TE signatures (changed in PR #2377 in TE 2.10)
# New signature (TE >= 2.10): forward(ctx, inp, non_tensor_args: Tuple, *weights_and_biases)
# Old signature (TE < 2.10): forward(ctx, inp, m_splits: List[int], use_bias, ...)
if Version("2.10") <= _TE_VERSION:
# New signature: non_tensor_args is a tuple, m_splits is the first element
num_gemms = len(args[idx + 1][0])
else:
# Old signature: m_splits is directly args[idx + 1]
num_gemms = len(args[idx + 1])

weights_and_biases = args[-2 * num_gemms :]
weights, biases = weights_and_biases[:num_gemms], weights_and_biases[num_gemms:]
quantized_inputs = self.input_quantizer(inp)
Expand Down