[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:
@@ -110,11 +110,7 @@ class ServingTokens(GenerateBaseServing):
|
||||
logger.error("Error with model %s", error_check_ret)
|
||||
return error_check_ret
|
||||
|
||||
# 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()
|
||||
|
||||
lora_request = None
|
||||
lora_request = self._maybe_get_adapters(request, supports_default_mm_loras=True)
|
||||
|
||||
Reference in New Issue
Block a user