Skip to content

[https://nvbugs/5355316] fix: update torch.compile option to fix triton store_cubin error #5865

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
merged 1 commit into from
Jul 10, 2025
Merged

[https://nvbugs/5355316] fix: update torch.compile option to fix triton store_cubin error #5865

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
2 changes: 1 addition & 1 deletion tensorrt_llm/_torch/modules/embedding.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,7 +123,7 @@ def get_masked_input_and_mask(


# We use torch.compile() to fuse the tiny pointwise ops before all_reduce/all_gather for Embedding module.
@torch.compile(mode="max-autotune-no-cudagraphs")
@torch.compile(options={"max-autotune": True})
def pre_comm_embedding_ops(
input_: torch.Tensor,
weight: torch.Tensor,
Expand Down
2 changes: 1 addition & 1 deletion tensorrt_llm/_torch/speculative/eagle3.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -335,7 +335,7 @@ def __init__(self, spec_config: Eagle3Config, mapping: Mapping):
self.max_draft_tokens = self.spec_config.max_draft_tokens
self.mapping = mapping

@torch.compile(mode="max-autotune-no-cudagraphs")
@torch.compile(options={"max-autotune": True})
def forward(self, input_ids, position_ids, hidden_states, logits,
attn_metadata, spec_metadata, draft_model):
batch_size = attn_metadata.num_seqs
Expand Down