Merge pull request #359 from nSircombe/feature/r25.08_updates

Updates to CHANGELOG and docs.

Author: cfRod

ML-Frameworks/pytorch-aarch64/CHANGELOG.md

@@ -15,7 +15,7 @@ where `YY` is the year, and `MM` the month of the increment.
 
 ### Fixed
 
-## [r25.08] 2025-08-27
+## [r25.08] 2025-08-28
 https://github.com/ARM-software/Tool-Solutions/tree/r25.08
 
 ### Added
@@ -43,6 +43,7 @@ https://github.com/ARM-software/Tool-Solutions/tree/r25.08
 
 ### Removed
 - https://github.com/pytorch/pytorch/pull/151547, to update OpenBLAS commit as this has been merged upstream.
+- Temporarily removed --compile flag from transformers_llm_text_gen.py example as there is an unresolved issue with torch compile support in this case.
 
 ### Fixed
 - Updates various Python packages to address known vulnerabilies with a high CVSS score:

ML-Frameworks/pytorch-aarch64/examples/README.md

@@ -224,24 +224,24 @@ LD_PRELOAD=/usr/lib/aarch64-linux-gnu/libtcmalloc.so.4    OMP_NUM_THREADS=16 pyt
 
 ### Text Generation
 
-The script [transformers_llm_text_gen.py](transformers_llm_text_gen.py) demonstrates how to generate text using Llama2 7B model via Transformers. It leverages the 4 bit dynamic quantization speedups and can supports vast number of text  models.
+The script [transformers_llm_text_gen.py](transformers_llm_text_gen.py) demonstrates how to generate text using TinyLlama-1.1B-Chat-v1.0 model via Transformers. It leverages the 4 bit dynamic quantization and can support a wide range of text models.
 
 Run inference using default (groupwise, layout-aware INT4) using tranformer call:
 
 ```
-LD_PRELOAD=/usr/lib/aarch64-linux-gnu/libtcmalloc.so.4  TORCHINDUCTOR_CPP_WRAPPER=1  TORCHINDUCTOR_FREEZING=1  OMP_NUM_THREADS=16 python transformers_llm_text_gen.py --compile
+LD_PRELOAD=/usr/lib/aarch64-linux-gnu/libtcmalloc.so.4  TORCHINDUCTOR_CPP_WRAPPER=1  TORCHINDUCTOR_FREEZING=1  OMP_NUM_THREADS=16 python transformers_llm_text_gen.py
 ```
 
 Run with symmetric_channelwise quantization:
 
 ```
-LD_PRELOAD=/usr/lib/aarch64-linux-gnu/libtcmalloc.so.4  TORCHINDUCTOR_CPP_WRAPPER=1  TORCHINDUCTOR_FREEZING=1  OMP_NUM_THREADS=16 python transformers_llm_text_gen.py --quant-scheme symmetric_channelwise --compile
+LD_PRELOAD=/usr/lib/aarch64-linux-gnu/libtcmalloc.so.4  TORCHINDUCTOR_CPP_WRAPPER=1  TORCHINDUCTOR_FREEZING=1  OMP_NUM_THREADS=16 python transformers_llm_text_gen.py --quant-scheme symmetric_channelwise
 ```
 
 Run with custom group size (e.g. 64):
 
 ```
-LD_PRELOAD=/usr/lib/aarch64-linux-gnu/libtcmalloc.so.4  TORCHINDUCTOR_CPP_WRAPPER=1  TORCHINDUCTOR_FREEZING=1  OMP_NUM_THREADS=16 python transformers_llm_text_gen.py --quant-scheme symmetric_groupwise --groupsize 64 --compile
+LD_PRELOAD=/usr/lib/aarch64-linux-gnu/libtcmalloc.so.4  TORCHINDUCTOR_CPP_WRAPPER=1  TORCHINDUCTOR_FREEZING=1  OMP_NUM_THREADS=16 python transformers_llm_text_gen.py --quant-scheme symmetric_groupwise --groupsize 64
 ```
 
 

ML-Frameworks/pytorch-aarch64/examples/llama_vision_instruct.py

@@ -126,7 +126,7 @@ def main(args):
     parser.add_argument(
         "--prompt",
         type=str,
-        default="Describe this image",
+        default="what is the animal in this image",
         help="Input prompt.",
     )
     parser.add_argument(

ML-Frameworks/tensorflow-aarch64/CHANGELOG.md

@@ -15,7 +15,7 @@ where `YY` is the year, and `MM` the month of the increment.
 
 ### Fixed
 
-## [r25.08] 2025-08-26
+## [r25.08] 2025-08-28
 https://github.com/ARM-software/Tool-Solutions/tree/r25.08
 
 ### Changed