We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
2 parents 90844af + 16ee249 commit 0bfa2d9Copy full SHA for 0bfa2d9
models/turbine_models/custom_models/llm_cmd_opts.py
@@ -44,8 +44,8 @@ def is_valid_file(arg):
44
)
45
46
##############################################################################
47
-# SDXL Inference Options
48
-# These options are used to control runtime parameters for SDXL inference.
+# Runtime Options
+# These options are used to control runtime parameters.
49
50
51
p.add_argument(
models/turbine_models/custom_models/stateless_llama.py
@@ -758,6 +758,9 @@ def format_out(results):
758
llama = StatelessLlama(
759
args.hf_model_name,
760
args.precision,
761
+ args.max_length,
762
+ args.batch_size,
763
+ args.num_inference_steps,
764
args.device,
765
args.iree_target_triple,
766
flags,
0 commit comments