Code
Hub
Workspaces
Connect
Indexed graphs
Engine
MCP
copy
hub
/
github.com/NVIDIA/TensorRT-LLM
/ empty
Method
empty
tensorrt_llm/llmapi/utils.py:389–390 ·
view source on GitHub ↗
(self)
Source
from the content-addressed store, hash-verified
387
return
len(self._q) == self._q.maxlen
388
389
def
empty(self) -> bool:
390
return
not self._q
391
392
def
put(self, item) -> None:
393
self._q.append(item)
Callers
15
apply_allocation
Function · 0.45
forward
Method · 0.45
topk_forward
Function · 0.45
forward
Method · 0.45
_compute_expt_data_internal
Function · 0.45
clear_sums
Function · 0.45
sum_bitmatrix_rows
Function · 0.45
alloc_fn
Function · 0.45
upcast_from_mxfp
Function · 0.45
unpad
Function · 0.45
forward
Method · 0.45
backward
Method · 0.45
Calls
no outgoing calls
Tested by
15
test_bert_attention
Method · 0.36
__init__
Method · 0.36
test_unet_runtime_float16
Method · 0.36
test_mamba
Method · 0.36
test_get_draft_token_array
Method · 0.36
test_packed_position_ids
Method · 0.36
test_beams2tree
Method · 0.36
load_test_cases
Method · 0.36
test_alibi_biases
Method · 0.36
test_mamba_conv1d
Method · 0.36
test_rg_lru
Method · 0.36
test_selective_scan_v2
Method · 0.36