Commitd0b56df

and

Guoming Zhang

authored

fix doc typo. (NVIDIA#114)

Co-authored-by: Guoming Zhang <37257613+nv-guomingz@users.noreply.github.com>

1 parent1c4a0ee commitd0b56dfCopy full SHA for d0b56df

File tree

-3

lines changed

-3

lines changed

Lines changed: 1 addition & 1 deletion

Lines changed: 2 additions & 2 deletions

Original file line number	Diff line number	Diff line change
`@@ -170,12 +170,12 @@ def test_int8_kv_cache(self):`
`170`	`170`	`self.assertTrue(qm.is_int8_weight_only())`
`171`	`171`
`172`	`172`	`deftest_failure_quant(self):`
`173`		`-# Expect failure if weights are notqunatized, but activations are.`
	`173`	`+# Expect failure if weights are notquantized, but activations are.`
`174`	`174`	`self.assertRaises(`
`175`	`175`	`ValueError,`
`176`	`176`	`lambda:QuantMode.from_description(False,True,False,False))`
`177`	`177`
`178`		`-# Expect failure if per token and per channel quantization, but weights and activations are notqunatized.`
	`178`	`+# Expect failure if per token and per channel quantization, but weights and activations are notquantized.`
`179`	`179`	`self.assertRaises(`
`180`	`180`	`ValueError,`
`181`	`181`	`lambda:QuantMode.from_description(False,False,True,True))`

Comments

(0)