Update after review

Review comments:
- #40 (review)

Signed-off-by: Martin Hickey <[email protected]>

Author: hickeyma

README.md

@@ -51,15 +51,15 @@ FMS Model Optimizer is a framework for developing reduced precision neural netwo
     - Clone the [CUTLASS](https://github.com/NVIDIA/cutlass) repository
     - `PyTorch 2.3.1` (as newer version will cause issue for the custom CUDA kernel used in these examples)
 - **FP8** is a reduced precision format like **INT8**:
-    - Nvidia H100 family or higher
+    - Nvidia A100 family or higher
     - [llm-compressor](https://github.com/vllm-project/llm-compressor)
 - To enable compute graph plotting function (mostly for troubleshooting purpose):
     - [matplotlib](https://matplotlib.org/)
     - [graphviz](https://graphviz.org/)
     - [pygraphviz](https://pygraphviz.github.io/)
 
 > [!NOTE]
-> PyTorch version should be < 2.5 if you would like to experiment deployment with external INT8 kernel.
+> PyTorch version should be < 2.4 if you would like to experiment deployment with external INT8 kernel.
 
 ### Installation
 

examples/FP8_QUANT/README.md

@@ -10,7 +10,7 @@ This is an example of mature FP8, which under the hood leverages some functional
 ## Requirements
 
 - [FMS Model Optimizer requirements](../../README.md#requirements)
-- Nvidia H100 family or higher
+- Nvidia A100 family or higher
 - The [llm-compressor](https://github.com/vllm-project/llm-compressor) library can be installed using pip:
 
     ```bash

pyproject.toml

@@ -21,7 +21,7 @@ classifiers=[
 ]
 dynamic = ["version"]
 dependencies = [
-"torch >=2.1, <2.5",
+"torch >=2.1, <2.4",
 "numpy",
 "tqdm",
 "tensorboard",