mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
9 lines
270 B
YAML
9 lines
270 B
YAML
inference_config:
|
|
impl_type: "inline"
|
|
inline_config:
|
|
checkpoint_type: "pytorch"
|
|
checkpoint_dir: {checkpoint_dir}/
|
|
tokenizer_path: {checkpoint_dir}/tokenizer.model
|
|
model_parallel_size: {model_parallel_size}
|
|
max_seq_len: 2048
|
|
max_batch_size: 1
|