[Core] Add max_num_queued_reqs and max_num_queued_tokens for queue size management (#49445)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
This commit is contained in:
@@ -440,11 +440,7 @@ class SpeechToTextBaseServing(GenerateBaseServing):
|
||||
if not request.model:
|
||||
request.model = self.models.model_name()
|
||||
|
||||
# If the engine is dead, raise the engine's DEAD_ERROR.
|
||||
# This is required for the streaming case, where we return a
|
||||
# success status before we actually start generating text :).
|
||||
if self.engine_client.errored:
|
||||
raise self.engine_client.dead_error
|
||||
self._preflight()
|
||||
|
||||
if request.response_format not in [
|
||||
"text",
|
||||
|
||||
Reference in New Issue
Block a user