more snippets

Signed-off-by: Shengliang Xu <shengliangx@nvidia.com>

Author: shengliangxu

modelopt_recipes/configs/ptq/w8a8_fp8_fp8.yaml

@@ -0,0 +1,25 @@
+# SPDX-FileCopyrightText: Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# W8A8 FP8: FP8 E4M3 weight and activation quantizers.
+imports:
+  fp8: configs/numerics/fp8
+---
+  - quantizer_name: '*weight_quantizer'
+    cfg:
+      $import: fp8
+  - quantizer_name: '*input_quantizer'
+    cfg:
+      $import: fp8

modelopt_recipes/general/ptq/fp8_default-fp8_kv.yaml

@@ -16,7 +16,7 @@
 imports:
   base_disable_all: configs/ptq/base_disable_all
   default_disabled: configs/ptq/default_disabled_quantizers
-  fp8: configs/numerics/fp8
+  w8a8_fp8_fp8: configs/ptq/w8a8_fp8_fp8
   fp8_kv: configs/ptq/fp8_kv
 
 metadata:
@@ -26,11 +26,6 @@ quantize:
   algorithm: max
   quant_cfg:
     - $import: base_disable_all
-    - quantizer_name: '*input_quantizer'
-      cfg:
-        $import: fp8
-    - quantizer_name: '*weight_quantizer'
-      cfg:
-        $import: fp8
+    - $import: w8a8_fp8_fp8
     - $import: fp8_kv
     - $import: default_disabled