The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Update quant doc so it's not completely wrong. (#13381)
comfyanonymous971932346ac6
diff --git a/QUANTIZATION.md b/QUANTIZATION.mdindex 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_s3. **Compute scales**: Derive `input_scale` from collected statistics4. **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.