We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent feb0c38 commit 1b22d86Copy full SHA for 1b22d86
examples/quantization_w8a8_fp8/fp8_block_example.py
@@ -15,9 +15,7 @@
15
# In this case, we:
16
# * quantize the weights to fp8 with per channel via ptq
17
# * quantize the activations to fp8 with dynamic per token
18
-recipe = QuantizationModifier(
19
- targets="Linear", scheme="FP8_BLOCK", ignore=["lm_head"]
20
-)
+recipe = QuantizationModifier(targets="Linear", scheme="FP8_BLOCK", ignore=["lm_head"])
21
22
# Apply quantization.
23
oneshot(model=model, recipe=recipe)
0 commit comments