Code
Hub
Workspaces
Connect
Indexed graphs
Engine
MCP
copy
hub
/
github.com/NVIDIA/TensorRT-LLM
/ error
Method
error
tensorrt_llm/logger.py:126–127 ·
view source on GitHub ↗
(self, *msg)
Source
from the content-addressed store, hash-verified
124
fatal_once = critical_once
125
126
def
error(self, *msg):
127
self.log(self.ERROR, *msg)
128
129
def
error_once(self, *msg, key):
130
self.log_once(self.ERROR, *msg, key=key)
Callers
15
replace_content
Function · 0.45
execute
Method · 0.45
_prepare_llm_response
Method · 0.45
_exec_triton_request
Method · 0.45
_exec_triton_request_single
Method · 0.45
send_cancellation_request
Method · 0.45
llm_quantization.py
File · 0.45
main
Function · 0.45
parse.py
File · 0.45
__init__
Method · 0.45
torch_split
Function · 0.45
__init__
Method · 0.45
Calls
1
log
Method · 0.95
Tested by
no test coverage detected