[Core][2/N] Model runner refactoring part 2. Combine prepare prefill / decode to a single API (#4681)

This PR combines prepare_prompt and prepare_decode into a single API. This PR also coelsce the attn metadata for prefill/decode to a single class and allow to slice them when running attn backend.

It also refactors subquery_start_loc which was not refactored in the previous PR
This commit is contained in:
SangBin Cho
2024-05-15 14:00:10 +09:00
committed by GitHub
parent 8a7cc254a0
commit 65bf2ac165
18 changed files with 781 additions and 734 deletions
+2 -1
View File
@@ -654,8 +654,9 @@ class SequenceGroupMetadata:
return self.lora_request.lora_int_id if self.lora_request else 0
@property
def token_chunk_size(self) -> Optional[int]:
def token_chunk_size(self) -> int:
"""Return the number of tokens to be processed (chunk size)."""
assert self._token_chunk_size is not None
return self._token_chunk_size