Code
Hub
Workspaces
Connect
Indexed graphs
Engine
MCP
copy
hub
/
github.com/NVIDIA/TensorRT-LLM
/ clear
Method
clear
tensorrt_llm/_torch/autotuner.py:380–381 ·
view source on GitHub ↗
(self)
Source
from the content-addressed store, hash-verified
378
return
len(self.cache)
379
380
def
clear(self) -> None:
381
self.cache.clear()
382
383
def
fallback_entry(self) -> Tuple:
384
# runner_id = 0, tactic = -1
Callers
10
reset
Method · 0.45
collect_dims_from_left
Method · 0.45
__post_init__
Method · 0.45
get
Method · 0.45
serve
Method · 0.45
mpi_future_callback
Method · 0.45
clear_cache
Method · 0.45
free_all_hostfunc_user_data
Function · 0.45
__del__
Method · 0.45
parse_streaming_increment
Method · 0.45
Calls
no outgoing calls
Tested by
no test coverage detected