Function float16_to_float32

src/mat.cpp:1970–2019 · view source on GitHub ↗

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

forwardMethod · 0.50

forward_fp16sMethod · 0.50

forwardMethod · 0.50

dynamic_quantizeMethod · 0.50

compute_A_tile_fp16_int8_scalesFunction · 0.50

pack_A_tile_fp16_to_int8Function · 0.50

transpose_compute_A_tile_fp16_int8_scalesFunction · 0.50

transpose_pack_A_tile_fp16_to_int8Function · 0.50

compute_B_fp16_int8_scaleFunction · 0.50

pack_B_tile_fp16_to_int8Function · 0.50

no outgoing calls

no test coverage detected