Skip to content
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

Adjusting max batch size in order to build TRT models on smaller GPUs #298

Merged
merged 1 commit into from
Apr 4, 2024
Merged

Adjusting max batch size in order to build TRT models on smaller GPUs #298

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 src/wordcab_transcribe/engines/tensorrt_llm/engine_builder/build.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,7 @@ def parse_arguments():
parser.add_argument("--quantize_dir", type=str, default="quantize/1-gpu")
parser.add_argument("--dtype", type=str, default="float16", choices=["float16"])
parser.add_argument("--log_level", type=str, default="info")
parser.add_argument("--max_batch_size", type=int, default=64)
parser.add_argument("--max_batch_size", type=int, default=24)
parser.add_argument("--max_input_len", type=int, default=4)
parser.add_argument("--max_output_len", type=int, default=448)
parser.add_argument("--max_beam_width", type=int, default=1)
Expand Down
2 changes: 1 addition & 1 deletion src/wordcab_transcribe/engines/tensorrt_llm/trt_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,7 @@ def get_session(self, engine_dir, runtime_mapping, debug_mode=False):

# TODO: Make dynamic max_batch_size and max_beam_width
decoder_model_config = ModelConfig(
max_batch_size=64,
max_batch_size=24,
max_beam_width=1,
num_heads=self.decoder_config["num_heads"],
num_kv_heads=self.decoder_config["num_heads"],
Expand Down
Loading