fix woq example and update document for v1.19.0

Signed-off-by: xin3he <[email protected]>
intel · Dec 23, 2024 · d366540 · d366540
1 parent 2186b0a
commit d366540
Show file tree

Hide file tree

Showing 4 changed files with 8 additions and 7 deletions.
diff --git a/.azure-pipelines/template/docker-template.yml b/.azure-pipelines/template/docker-template.yml
@@ -74,7 +74,7 @@ steps:
 
   - ${{ if eq(parameters.imageSource, 'pull') }}:
       - script: |
-            docker pull vault.habana.ai/gaudi-docker/1.18.0/ubuntu22.04/habanalabs/pytorch-installer-2.4.0:latest
+            docker pull vault.habana.ai/gaudi-docker/1.19.0/ubuntu24.04/habanalabs/pytorch-installer-2.5.1:latest
         displayName: "Pull habana docker image"
 
   - script: |
@@ -95,7 +95,7 @@ steps:
             else
                 docker run -dit --disable-content-trust --privileged --name=${{ parameters.containerName }} --shm-size="2g" \
                 --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --net=host --ipc=host \
-                -v ${BUILD_SOURCESDIRECTORY}:/neural-compressor vault.habana.ai/gaudi-docker/1.18.0/ubuntu22.04/habanalabs/pytorch-installer-2.4.0:latest
+                -v ${BUILD_SOURCESDIRECTORY}:/neural-compressor vault.habana.ai/gaudi-docker/1.19.0/ubuntu24.04/habanalabs/pytorch-installer-2.5.1:latest
             fi
             echo "Show the container list after docker run ... "
             docker ps -a

diff --git a/README.md b/README.md
@@ -78,7 +78,7 @@ Following example code demonstrates FP8 Quantization, it is supported by Intel G
 To try on Intel Gaudi2, docker image with Gaudi Software Stack is recommended, please refer to following script for environment setup. More details can be found in [Gaudi Guide](https://docs.habana.ai/en/latest/Installation_Guide/Bare_Metal_Fresh_OS.html#launch-docker-image-that-was-built).
 ```bash
 # Run a container with an interactive shell
-docker run -it --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --net=host --ipc=host vault.habana.ai/gaudi-docker/1.18.0/ubuntu22.04/habanalabs/pytorch-installer-2.4.0:latest
+docker run -it --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --net=host --ipc=host vault.habana.ai/gaudi-docker/1.19.0/ubuntu24.04/habanalabs/pytorch-installer-2.5.1:latest
 ```
 Run the example:
 ```python

diff --git a/...h/nlp/huggingface_models/language-modeling/quantization/weight_only/run_clm_no_trainer.py b/...h/nlp/huggingface_models/language-modeling/quantization/weight_only/run_clm_no_trainer.py
@@ -270,8 +270,9 @@ def get_user_model():
         torchscript = True
     if args.woq_algo == "AutoRound" and is_habana_framework_installed():
         print("Quantizing model with AutoRound on HPU")
-        check_torch_compile_with_hpu_backend()
-        set_envs_for_torch_compile_with_hpu_backend()
+        if args.quantize:
+            check_torch_compile_with_hpu_backend()
+            set_envs_for_torch_compile_with_hpu_backend()
         user_model = AutoModelForCausalLM.from_pretrained(
             args.model,
             trust_remote_code=args.trust_remote_code,
@@ -568,7 +569,7 @@ def run_fn_for_gptq(model, dataloader_for_calibration, *args):
 
 
 if is_hpex_available():
-    from habana_frameworks.torch.hpu import wrap_in_hpu_graph
+    from habana_frameworks.torch.hpu.graphs import wrap_in_hpu_graph
     user_model = user_model.to(torch.bfloat16)
     wrap_in_hpu_graph(user_model, max_graphs=10)
 

diff --git a/test/3x/torch/requirements.txt b/test/3x/torch/requirements.txt
@@ -1,5 +1,5 @@
 auto_round
-deepspeed @ git+https://github.com/HabanaAI/DeepSpeed.git@1.18.0
+deepspeed @ git+https://github.com/HabanaAI/DeepSpeed.git@1.19.0
 expecttest
 intel_extension_for_pytorch
 numpy