From 971932346ac6e6e02c1e1e8cfe34df2f0e1cea3e Mon Sep 17 00:00:00 2001
From: comfyanonymous <121283862+comfyanonymous@users.noreply.github.com>
Date: Sun, 12 Apr 2026 20:27:38 -0700
Subject: [PATCH] Update quant doc so it's not completely wrong. (#13381)

There is still more that needs to be fixed.
---
 QUANTIZATION.md | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/QUANTIZATION.md b/QUANTIZATION.md
index 1693e13f3..300822029 100644
--- a/QUANTIZATION.md
+++ b/QUANTIZATION.md
@@ -139,9 +139,9 @@ Example:
   "_quantization_metadata": {
     "format_version": "1.0",
     "layers": {
-      "model.layers.0.mlp.up_proj": "float8_e4m3fn",
-      "model.layers.0.mlp.down_proj": "float8_e4m3fn",
-      "model.layers.1.mlp.up_proj": "float8_e4m3fn"
+      "model.layers.0.mlp.up_proj": {"format": "float8_e4m3fn"},
+      "model.layers.0.mlp.down_proj": {"format": "float8_e4m3fn"},
+      "model.layers.1.mlp.up_proj": {"format": "float8_e4m3fn"}
     }
   }
 }
@@ -165,4 +165,4 @@ Activation quantization (e.g., for FP8 Tensor Core operations) requires `input_s
 3. **Compute scales**: Derive `input_scale` from collected statistics
 4. **Store in checkpoint**: Save `input_scale` parameters alongside weights
 
-The calibration dataset should be representative of your target use case. For diffusion models, this typically means a diverse set of prompts and generation parameters.
\ No newline at end of file
+The calibration dataset should be representative of your target use case. For diffusion models, this typically means a diverse set of prompts and generation parameters.