Method step

deepspeed/runtime/quantize.py:75–76 · view source on GitHub ↗

(self)

Source from the content-addressed store, hash-verified

73	p.data = self.compute_quantization(p, layer_id)
74
75	def step(self):
76	self.qsteps += 1
77
78	def quantize_highbit(self, inputs, num_bits):
79

quantizeMethod · 0.95

mainFunction · 0.45

no outgoing calls

no test coverage detected