[Doc] Consistent naming of attention backends (#9498)

Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
This commit is contained in:
Thomas Parnell
2024-10-21 22:29:57 +08:00
committed by GitHub
parent 696b01af8f
commit 496e991da8
14 changed files with 23 additions and 19 deletions
+1 -1
View File
@@ -184,7 +184,7 @@ class SpecDecodeWorker(LoraNotSupportedWorkerBase):
if not disable_mqa_scorer:
if scorer_worker.model_runner.attn_backend.get_name(
) != "flash-attn":
) != "FLASH_ATTN":
disable_mqa_scorer = True
logger.info(
"[Speculative Decoding] Disabling MQA scorer as the "