Code
Hub
Workspaces
Connect
Indexed graphs
Engine
MCP
copy
hub
/
github.com/NVIDIA/TensorRT-LLM
/ warning_once
Method
warning_once
tensorrt_llm/logger.py:135–136 ·
view source on GitHub ↗
(self, *msg, key)
Source
from the content-addressed store, hash-verified
133
self.log(self.WARNING, *msg)
134
135
def
warning_once(self, *msg, key):
136
self.log_once(self.WARNING, *msg, key=key)
137
138
def
info(self, *msg):
139
self.log(self.INFO, *msg)
Callers
11
balanced_run_moe
Function · 0.80
_serialize_cache_data
Method · 0.80
_deserialize_cache_data
Method · 0.80
choose_one
Method · 0.80
_profile_runners
Method · 0.80
load_weight_shard
Function · 0.80
_ensure_contiguous_with_dtype
Method · 0.80
forward_sparse_mla_kvcache_bf16
Method · 0.80
rotate_activation
Function · 0.80
pack_image_features
Method · 0.80
modeling_exaone_moe.py
File · 0.80
Calls
1
log_once
Method · 0.95
Tested by
no test coverage detected