Fix install instructions and pyproject.tomls (#11781)
This commit is contained in:
@@ -623,7 +623,7 @@ class ModelRunner:
|
||||
server_args.disable_chunked_prefix_cache = True
|
||||
|
||||
if not server_args.disable_chunked_prefix_cache:
|
||||
logger.info("Chunked prefix cache is turned on.")
|
||||
log_info_on_rank0(logger, "Chunked prefix cache is turned on.")
|
||||
|
||||
if server_args.attention_backend == "aiter":
|
||||
if self.model_config.context_len > 8192:
|
||||
|
||||
Reference in New Issue
Block a user