roundup_power2_divisions not needed with newer pytorch versions (#3540)

* roundup_power2_divisions not needed with newer pytorch versions

* remove typo

* update qwen3.5 moe 35b-a3b yaml for 5090

* more bug fixes

* fix tests to match updated trainer

* don't use fa2 for hooks test

* reset plugins on the instance

* retry download

* fix references to renamed axolotl_cfg property on trainer

* Fix ref to trainer cfg

cicd/cicd.sh

@@ -4,7 +4,17 @@ set -e
 python -c "import torch; assert '$PYTORCH_VERSION' in torch.__version__"
 
 set -o pipefail
-curl --silent --show-error --fail --retry 3 --retry-delay 5 -L https://axolotl-ci.b-cdn.net/hf-cache.tar.zst | tar -xpf - -C "${HF_HOME}/hub/" --use-compress-program unzstd --strip-components=1
+for i in 1 2 3; do
+  if curl --silent --show-error --fail -L \
+    https://axolotl-ci.b-cdn.net/hf-cache.tar.zst \
+    | tar -xpf - -C "${HF_HOME}/hub/" --use-compress-program unzstd --strip-components=1; then
+    echo "HF cache extracted successfully"
+    break
+  fi
+  echo "Attempt $i failed, cleaning up and retrying in 15s..."
+  rm -rf "${HF_HOME}/hub/"*
+  sleep 15
+done
 # hf download "NousResearch/Meta-Llama-3-8B"
 # hf download "NousResearch/Meta-Llama-3-8B-Instruct"
 # hf download "microsoft/Phi-4-reasoning"