MCPcopy Index your code
hub / github.com/NVIDIA/TensorRT-LLM / has_fp8_kv_cache

Method has_fp8_kv_cache

tensorrt_llm/quantization/mode.py:167–168  ·  view source on GitHub ↗
(self)

Source from the content-addressed store, hash-verified

165 return self._any(self.INT8_KV_CACHE)
166
167 def has_fp8_kv_cache(self):
168 return self._any(self.FP8_KV_CACHE)
169
170 def has_fp4_kv_cache(self):
171 return self._any(self.NVFP4_KV_CACHE)

Callers 15

has_kv_cache_quantMethod · 0.95
to_dictMethod · 0.95
create_builder_configMethod · 0.80
buildFunction · 0.80
update_quant_configMethod · 0.80
forwardMethod · 0.80
update_quant_configMethod · 0.80
_single_request_preprocess_inputsMethod · 0.80
get_cache_size_per_tokenMethod · 0.80
get_cache_size_per_tokenMethod · 0.80
__init__Method · 0.80
_create_kv_cache_managerFunction · 0.80

Calls 1

_anyMethod · 0.95

Tested by

no test coverage detected