Code
Hub
Workspaces
Connect
Indexed graphs
Engine
MCP
copy
hub
/
github.com/NVIDIA/TensorRT-LLM
/ unsqueeze
Method
unsqueeze
tensorrt_llm/functional.py:462–466 ·
view source on GitHub ↗
See functional.squeeze.
(self, dim)
Source
from the content-addressed store, hash-verified
460
return
squeeze(self, dim, zero_is_placeholder)
461
462
def
unsqueeze(self, dim):
463
''
&
#x27;
464
See functional.squeeze.
465
''
&
#x27;
466
return
unsqueeze(self, dim)
467
468
def
log(self):
469
''
&
#x27;
Callers
15
build_alibi_tensor
Function · 0.95
compaction_torch
Function · 0.80
upcast_from_mxfp_torch
Function · 0.80
_test_additional_model_outputs_integration
Function · 0.80
test_gpt_attention
Method · 0.80
tile_beam_width
Method · 0.80
torch_exec
Method · 0.80
test_vgqa_model_runner_allclose
Method · 0.80
test_mamba
Method · 0.80
test_loaders
Method · 0.80
check_accuracy
Function · 0.80
test_get_draft_token_array
Method · 0.80
Calls
1
unsqueeze
Function · 0.85
Tested by
15
_test_additional_model_outputs_integration
Function · 0.64
test_gpt_attention
Method · 0.64
tile_beam_width
Method · 0.64
torch_exec
Method · 0.64
test_vgqa_model_runner_allclose
Method · 0.64
test_mamba
Method · 0.64
test_loaders
Method · 0.64
check_accuracy
Function · 0.64
test_get_draft_token_array
Method · 0.64
test_unpack_gen_data
Method · 0.64
test_beams2tree
Method · 0.64
quant_dequant_int
Function · 0.64