[BUGFIX][Quant]Fix test_kv_scale_reload failed (#50405)
Signed-off-by: Lai, Yejing <yejing.lai@intel.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
c416f15710
commit
2cb3ff88cc
+3
-2
@@ -137,8 +137,9 @@ class CompressedTensorsW8A16Fp8(CompressedTensorsScheme):
|
|||||||
"weight_scale",
|
"weight_scale",
|
||||||
convert_to_channelwise(layer.weight_scale, layer.logical_widths),
|
convert_to_channelwise(layer.weight_scale, layer.logical_widths),
|
||||||
)
|
)
|
||||||
self.strategy = QuantizationStrategy.CHANNEL
|
self.weight_quant_key = STRATEGY_TO_WEIGHT_QUANT_KEY[
|
||||||
self.weight_quant_key = STRATEGY_TO_WEIGHT_QUANT_KEY[self.strategy]
|
QuantizationStrategy.CHANNEL
|
||||||
|
]
|
||||||
self.linear_kernel.config.weight_quant_key = self.weight_quant_key
|
self.linear_kernel.config.weight_quant_key = self.weight_quant_key
|
||||||
|
|
||||||
# Canonicalize to (K, N) for the kernel.
|
# Canonicalize to (K, N) for the kernel.
|
||||||
|
|||||||
Reference in New Issue
Block a user