Skip to content

[https://nvbugs/5451342][fix] Use runtime max_batch_size when cuda_graph_config.max_batch_size is not provided in trtllm-bench #7031

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 3 commits into from
Aug 26, 2025
Merged

[https://nvbugs/5451342][fix] Use runtime max_batch_size when cuda_graph_config.max_batch_size is not provided in trtllm-bench #7031

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
cc3beac
use runtime max_batch_size if cuda_graph_config.max_batch_size is not…
jiaganc Aug 19, 2025
93d792d
decrease kvcache fraction to avoid OOM
jiaganc Aug 20, 2025
6c7142f
limit the changes in trtllm-bench to avoid OOM in CI
jiaganc Aug 21, 2025
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
20 changes: 18 additions & 2 deletions tensorrt_llm/bench/dataclasses/configuration.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,8 +84,24 @@ def get_llm_args(self) -> Dict:
backend_cache_config = llm_args.pop("kv_cache_config", {})
llm_args["kv_cache_config"] = backend_cache_config | kv_cache_config

return update_llm_args_with_extra_options(llm_args,
self.extra_llm_api_options)
updated_llm_args = update_llm_args_with_extra_options(
llm_args, self.extra_llm_api_options)

if self.backend == "pytorch":
cuda_graph_config = updated_llm_args.pop(
"cuda_graph_config", llm_args["cuda_graph_config"])
# Use runtime max_batch_size as cuda_graph_config.max_batch_size
# if both max_batch_size and batch_sizes are not set.
batch_sizes_set = cuda_graph_config.get("batch_sizes",
None) is not None
max_batch_size_set = cuda_graph_config.get("max_batch_size",
None) is not None
if not batch_sizes_set and not max_batch_size_set:
cuda_graph_config[
"max_batch_size"] = self.settings_config.max_batch_size
updated_llm_args["cuda_graph_config"] = cuda_graph_config

return updated_llm_args

@model_validator(mode="after")
def validate_full_config(self) -> RuntimeConfig:
Expand Down