QAT (#2590)

QAT and quantization w/torchao

_quarto.yml

@@ -43,6 +43,7 @@ quartodoc:
         - cli.vllm_serve
         - cli.cloud.base
         - cli.cloud.modal_
+        - cli.quantize
     - title: Trainers
       desc: Training implementations
       contents:
@@ -147,6 +148,7 @@ quartodoc:
         - utils.optimizers.adopt
         - utils.data.pretraining
         - utils.data.sft
+        - utils.quantization
     - title: Schemas
       desc: Pydantic data models for Axolotl config
       contents:
@@ -196,7 +198,7 @@ quartodoc:
         - utils.callbacks.lisa
         - utils.callbacks.mlflow_
         - utils.callbacks.comet_
-
+        - utils.callbacks.qat
 website:
   title: "Axolotl"
   description: "We make fine-tuning accessible, scalable, and fun"
@@ -256,6 +258,8 @@ website:
             - docs/lr_groups.qmd
             - docs/lora_optims.qmd
             - docs/dataset_loading.qmd
+            - docs/qat.qmd
+            - docs/quantize.qmd
 
         - section: "Core Concepts"
           contents: