Code
Hub
Workspaces
Connect
Indexed graphs
Engine
MCP
copy
hub
/
github.com/NVIDIA/TensorRT-LLM
/ has_nvfp4
Method
has_nvfp4
tensorrt_llm/quantization/mode.py:183–184 ·
view source on GitHub ↗
(self)
Source
from the content-addressed store, hash-verified
181
return
self._any(self.FP8_ROWWISE)
182
183
def
has_nvfp4(self):
184
return
self._any(self.NVFP4)
185
186
def
has_w4a8_nvfp4_fp8(self):
187
return
self._any(self.W4A8_NVFP4_FP8)
Callers
15
test_mlp_comparison
Method · 0.95
test_ootb_comparison
Method · 0.95
to_dict
Method · 0.95
MLP
Method · 0.45
set_weight_layer
Method · 0.45
create_trt_session
Method · 0.45
build
Function · 0.45
_load_model_from_hf
Method · 0.45
fp4_quantize
Function · 0.45
quantize
Function · 0.45
_moe_plugin
Function · 0.45
__init__
Method · 0.45
Calls
1
_any
Method · 0.95
Tested by
5
test_mlp_comparison
Method · 0.76
test_ootb_comparison
Method · 0.76
MLP
Method · 0.36
set_weight_layer
Method · 0.36
create_trt_session
Method · 0.36