For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).
Mojo function
ep_token_index_offset
def ep_token_index_offset(*, n_ranks: Int, max_tokens_per_rank: Int, msg_bytes: Int) -> Int
Returns where a token_recv receive buffer's token indices start.
Args:
- โn_ranks (
Int): The number of devices participating in communication. - โmax_tokens_per_rank (
Int): The maximum number of tokens per rank. - โmsg_bytes (
Int): The token format's message size.
Returns:
Int: The byte offset past the messages, aligned to a token index.