[PP] Fix init_memory_pool desync & add PP for mixtral (#6223)

2025-05-12 12:38:09 -07:00
parent 12319a6787
commit bad7c26fdc
8 changed files with 179 additions and 47 deletions
@@ -468,9 +468,6 @@ class PrefillAdder:
            return AddReqResult.OTHER

        with self._lock_node(req.last_node):
-            if total_tokens > self.rem_total_tokens:
-                return AddReqResult.NO_TOKEN
-
            if (
                enable_hierarchical_cache
                and req.last_node_global is not None