Revert "make radix cache deterministic" (#11728)
This commit is contained in:
@@ -1411,6 +1411,13 @@ class ServerArgs:
|
||||
f"Currently only {DETERMINISTIC_ATTENTION_BACKEND_CHOICES} attention backends are supported for deterministic inference."
|
||||
)
|
||||
|
||||
# Currently, only FA3 supports radix cache. Support for other backends is in progress
|
||||
if self.attention_backend != "fa3":
|
||||
self.disable_radix_cache = True
|
||||
logger.warning(
|
||||
f"Currently radix cache is not compatible with {self.attention_backend} attention backend for deterministic inference. It will be supported in the future."
|
||||
)
|
||||
|
||||
# Check TP size
|
||||
if self.tp_size > 1:
|
||||
os.environ["NCCL_ALGO"] = "allreduce:tree"
|
||||
|
||||
Reference in New Issue
Block a user