For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).
Mojo function
compute_log_probabilities_ragged_shape
def compute_log_probabilities_ragged_shape[levels: Int](logits: ManagedTensorSlice[Input, static_spec=logits.static_spec], tokens: ManagedTensorSlice[Input, static_spec=tokens.static_spec], sampled_tokens: ManagedTensorSlice[Input, static_spec=sampled_tokens.static_spec], logit_row_offsets: ManagedTensorSlice[Input, static_spec=logit_row_offsets.static_spec], token_row_offsets: ManagedTensorSlice[Input, static_spec=token_row_offsets.static_spec], lp_output_offsets: ManagedTensorSlice[Input, static_spec=lp_output_offsets.static_spec], lp_output_offsets_host: ManagedTensorSlice[Input, static_spec=lp_output_offsets_host.static_spec]) -> IndexList[Int(2)]
Returns:
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!