Skip to content

[None][fix] piecewise cudagraph node name for gemma-3-1b-it #12131

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

Open
amukkara wants to merge 1 commit into
base: main
Choose a base branch
from
Open

[None][fix] piecewise cudagraph node name for gemma-3-1b-it #12131

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
1 change: 0 additions & 1 deletion examples/llm-api/quickstart_advanced.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -305,7 +305,6 @@ def setup_llm(args, **kwargs):
enable_iter_perf_stats=args.print_iter_log,
torch_compile_config=TorchCompileConfig(
enable_fullgraph=args.use_torch_compile,
enable_inductor=args.use_torch_compile,
enable_piecewise_cuda_graph= \
args.use_piecewise_cuda_graph)
if args.use_torch_compile else None,
Expand Down
3 changes: 2 additions & 1 deletion tensorrt_llm/_torch/compilation/backend.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -146,9 +146,10 @@ def __call__(self, gm: GraphModule,
)
return gm

self.input_num_tokens = None
for node in gm.graph.nodes:
if node.op == "placeholder":
if node.name == "l_input_ids_":
if node.name in ["l_input_ids_", "l_kwargs_input_ids_"]:
example_value = node.meta["example_value"]
assert isinstance(example_value, FakeTensor)
self.input_num_tokens = example_value.shape[0]
Expand Down
Loading