Merge branch 'main' into lcalabri/ci_test_lang_mod_eager_lazy

Author: Luca-Calabria

.github/workflows/fast_tests.yml

@@ -15,7 +15,7 @@ concurrency:
 jobs:
   transformers:
     name: Run tests for optimum.habana.transformers
-    runs-on: [self-hosted, linux, x64, gaudi2]
+    runs-on: [self-hosted, linux, x64, gaudi2, fast]
     steps:
       - name: Checkout
         uses: actions/checkout@v2
@@ -25,19 +25,22 @@ jobs:
       - name: Run tests
         run: |
             docker run \
+            --rm \
             -v $PWD:/root/workspace \
+            -v /scratch-1:/data \
             --workdir=/root/workspace \
             --runtime=habana \
-            -e HABANA_VISIBLE_DEVICES=all \
+            -e HABANA_VISIBLE_DEVICES=$DOCKER_HABANA_VISIBLE_DEVICES \
             -e OMPI_MCA_btl_vader_single_copy_mechanism=none \
+            -e HF_HOME=/data \
             --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 \
             /bin/bash tests/ci/fast_tests.sh
   diffusers:
     name: Run tests for optimum.habana.diffusers
-    runs-on: [self-hosted, linux, x64, gaudi2]
+    runs-on: [self-hosted, linux, x64, gaudi2, fast]
     steps:
       - name: Checkout
         uses: actions/checkout@v2
@@ -47,11 +50,14 @@ jobs:
       - name: Run tests
         run: |
             docker run \
+            --rm \
             -v $PWD:/root/workspace \
+            -v /scratch-1:/data \
             --workdir=/root/workspace \
             --runtime=habana \
-            -e HABANA_VISIBLE_DEVICES=all \
+            -e HABANA_VISIBLE_DEVICES=$DOCKER_HABANA_VISIBLE_DEVICES \
             -e OMPI_MCA_btl_vader_single_copy_mechanism=none \
+            -e HF_HOME=/data \
             --cap-add=sys_nice \
             --net=host \
             --ipc=host \

.github/workflows/slow_tests_gaudi2.yml

@@ -9,9 +9,35 @@ concurrency:
   group: ${{ github.workflow }}
 
 jobs:
+  example-diff:
+    name: Test examples differences
+    runs-on: [self-hosted, linux, x64, gaudi2, nightly]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+      - name: Pull image
+        run: |
+            docker pull vault.habana.ai/gaudi-docker/1.18.0/ubuntu22.04/habanalabs/pytorch-installer-2.4.0:latest
+      - name: Run tests
+        run: |
+            docker run \
+            --rm \
+            -v $PWD:/root/workspace \
+            --workdir=/root/workspace \
+            --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 \
+            /bin/bash tests/ci/example_diff_tests.sh
   stable-diffusion:
     name: Test Stable Diffusion
-    runs-on: [self-hosted, linux, x64, gaudi2]
+    if: ${{ !cancelled() && (success() || failure()) }}
+    needs:
+      - example-diff  # run the job when the previous test job is done
+    runs-on: [self-hosted, linux, x64, gaudi2, nightly]
     steps:
       - name: Checkout
         uses: actions/checkout@v2
@@ -40,7 +66,7 @@ jobs:
     if: ${{ !cancelled() && (success() || failure()) }}
     needs:
       - stable-diffusion  # run the job when the previous test job is done
-    runs-on: [self-hosted, linux, x64, gaudi2]
+    runs-on: [self-hosted, linux, x64, gaudi2, nightly]
     steps:
       - name: Checkout
         uses: actions/checkout@v2
@@ -69,7 +95,7 @@ jobs:
     if: ${{ !cancelled() && (success() || failure()) }}
     needs:
       - deepspeed  # run the job when the previous test job is done
-    runs-on: [self-hosted, linux, x64, gaudi2]
+    runs-on: [self-hosted, linux, x64, gaudi2, nightly]
     steps:
       - name: Checkout
         uses: actions/checkout@v2
@@ -98,7 +124,7 @@ jobs:
     if: ${{ !cancelled() && (success() || failure()) }}
     needs:
       - fsdp  # run the job when the previous test job is done
-    runs-on: [self-hosted, linux, x64, gaudi2]
+    runs-on: [self-hosted, linux, x64, gaudi2, nightly]
     steps:
       - name: Checkout
         uses: actions/checkout@v2
@@ -128,7 +154,7 @@ jobs:
     needs:
       - deepspeed
       - multi-card  # run the job when the previous test jobs are done
-    runs-on: [self-hosted, linux, x64, gaudi2]
+    runs-on: [self-hosted, linux, x64, gaudi2, nightly]
     steps:
       - name: Checkout
         uses: actions/checkout@v2
@@ -160,7 +186,7 @@ jobs:
       - deepspeed
       - multi-card
       - single-card  # run the job when the previous test jobs are done
-    runs-on: [self-hosted, linux, x64, gaudi2]
+    runs-on: [self-hosted, linux, x64, gaudi2, nightly]
     steps:
       - name: Checkout
         uses: actions/checkout@v2
@@ -189,7 +215,7 @@ jobs:
     if: ${{ !cancelled() && (success() || failure()) }}
     needs:
       - text-generation
-    runs-on: [self-hosted, linux, x64, gaudi2]
+    runs-on: [self-hosted, linux, x64, gaudi2, nightly]
     steps:
       - name: Checkout
         uses: actions/checkout@v2
@@ -218,7 +244,7 @@ jobs:
     if: ${{ !cancelled() && (success() || failure()) }}
     needs:
       - trl
-    runs-on: [self-hosted, linux, x64, gaudi2]
+    runs-on: [self-hosted, linux, x64, gaudi2, nightly]
     steps:
       - name: Checkout Optimum Habana
         uses: actions/checkout@v2

README.md

@@ -214,6 +214,7 @@ The following model architectures, tasks and device distributions have been vali
 | Qwen2 | <div style="text-align:left"><li>Single card</li></div> | <div style="text-align:left"><li>Single card</li></div> | <li>[language modeling](https://github.com/huggingface/optimum-habana/tree/main/examples/language-modeling)</li><li>[text generation](https://github.com/huggingface/optimum-habana/tree/main/examples/text-generation)</li> |
 | Qwen2-MoE |   | <div style="text-align:left"><li>Single card</li></div> | <li>[text generation](https://github.com/huggingface/optimum-habana/tree/main/examples/text-generation)</li> |
 | Gemma | :heavy_check_mark:  | <div style="text-align:left"><li>Single card</li></div> | <li>[language modeling](https://github.com/huggingface/optimum-habana/tree/main/examples/language-modeling)</li><li>[text generation](https://github.com/huggingface/optimum-habana/tree/main/examples/text-generation)</li> |
+| Gemma2 |  | :heavy_check_mark: | <li>[text generation](https://github.com/huggingface/optimum-habana/tree/main/examples/text-generation)</li> |
 | XGLM | | <div style="text-align:left"><li>Single card</li></div> | <li>[text generation](https://github.com/huggingface/optimum-habana/tree/main/examples/text-generation)</li> |
 | Cohere       |          | <div style="text-align:left"><li>Single card</li></div> | <li>[text generation](https://github.com/huggingface/optimum-habana/tree/main/examples/text-generation)</li> |
 | T5 / Flan T5 | :heavy_check_mark: | :heavy_check_mark: | <li>[summarization](https://github.com/huggingface/optimum-habana/tree/main/examples/summarization)</li><li>[translation](https://github.com/huggingface/optimum-habana/tree/main/examples/translation)</li><li>[question answering](https://github.com/huggingface/optimum-habana/tree/main/examples/question-answering#fine-tuning-t5-on-squad20)</li> |
@@ -231,11 +232,14 @@ The following model architectures, tasks and device distributions have been vali
 | ClipSeg |   | <div style="text-align:left"><li>Single card</li></div> | <li>[object segmentation](https://github.com/huggingface/optimum-habana/tree/main/examples/object-segementation)</li> |
 | Llava / Llava-next |    | <div style="text-align:left"><li>Single card</li></div> | <li>[image to text](https://github.com/huggingface/optimum-habana/tree/main/examples/image-to-text)</li> |
 | idefics2 | <div style="text-align:left"><li>LoRA</li></div> | <div style="text-align:left"><li>Single card</li></div> | <li>[image to text](https://github.com/huggingface/optimum-habana/tree/main/examples/image-to-text)</li> |
+| Paligemma | | <div style="text-align:left"><li>Single card</li></div> | <li>[image to text](https://github.com/huggingface/optimum-habana/tree/main/examples/image-to-text)</li> |
 | Segment Anything Model |   | <div style="text-align:left"><li>Single card</li></div> | <li>[object segmentation](https://github.com/huggingface/optimum-habana/tree/main/examples/object-segementation)</li> |
 | VideoMAE | | <div style="text-align:left"><li>Single card</li></div> | <li>[Video classification](https://github.com/huggingface/optimum-habana/tree/main/examples/video-classification)</li> |
 | TableTransformer |   | <div style="text-align:left"><li>Single card</li></div> | <li>[table object detection](https://github.com/huggingface/optimum-habana/tree/main/examples/table-detection) </li> |
 | DETR |   | <div style="text-align:left"><li>Single card</li></div> | <li>[object detection](https://github.com/huggingface/optimum-habana/tree/main/examples/object-detection)</li> |
 | Mllama     | <div style="text-align:left"><li>LoRA</li></div> | :heavy_check_mark: | <li>[image to text](https://github.com/huggingface/optimum-habana/tree/main/examples/image-to-text)</li> |
+| MiniCPM3 |   | <div style="text-align:left"><li>Single card</li></div> | <li>[text generation](https://github.com/huggingface/optimum-habana/tree/main/examples/text-generation)</li> |
+| Baichuan2 |   | <div style="text-align:left"><li>Single card</li></div> | <li>[text generation](https://github.com/huggingface/optimum-habana/tree/main/examples/text-generation)</li> |
 
 </div>
 
@@ -249,6 +253,7 @@ The following model architectures, tasks and device distributions have been vali
 | Stable Diffusion XL | <li>[fine-tuning](https://github.com/huggingface/optimum-habana/tree/main/examples/stable-diffusion/training#fine-tuning-for-stable-diffusion-xl)</li> | <li>Single card</li> | <li>[text-to-image generation](https://github.com/huggingface/optimum-habana/tree/main/examples/stable-diffusion)</li> |
 | Stable Diffusion Depth2img | | <li>Single card</li> | <li>[depth-to-image generation](https://github.com/huggingface/optimum-habana/tree/main/examples/stable-diffusion)</li> |
 | LDM3D            |          | <li>Single card</li> | <li>[text-to-image generation](https://github.com/huggingface/optimum-habana/tree/main/examples/stable-diffusion)</li> |
+| FLUX.1           | <li>[fine-tuning](https://github.com/huggingface/optimum-habana/tree/main/examples/stable-diffusion/training#dreambooth-lora-fine-tuning-with-flux1-dev)</li> | <li>Single card</li> | <li>[text-to-image generation](https://github.com/huggingface/optimum-habana/tree/main/examples/stable-diffusion)</li> |
 | Text to Video    |          | <li>Single card</li> | <li>[text-to-video generation](https://github.com/huggingface/optimum-habana/tree/main/examples/text-to-video)</li> |
 
 </div>

docs/source/_toctree.yml

@@ -1,6 +1,6 @@
 - sections:
   - local: index
-    title: 🤗 Optimum Habana
+    title: 🤗 Optimum for Intel Gaudi
   - local: installation
     title: Installation
   - local: quickstart
@@ -16,12 +16,14 @@
       title: Run Inference
     - local: tutorials/stable_diffusion
       title: Stable Diffusion
-    - local: tutorials/stable_diffusion_ldm3d
-      title: LDM3D
+    - local: tutorials/tgi
+      title: TGI on Gaudi
     title: Tutorials
   - sections:
     - local: usage_guides/overview
       title: Overview
+    - local: usage_guides/script_adaptation
+      title: Script Adaptation
     - local: usage_guides/pretraining
       title: Pretraining Transformers
     - local: usage_guides/accelerate_training
@@ -32,20 +34,16 @@
       title: How to use DeepSpeed
     - local: usage_guides/multi_node_training
       title: Multi-node Training
+    - local: usage_guides/quantization
+      title: Quantization
     title: How-To Guides
-  - sections:
-    - local: concept_guides/hpu
-      title: What are Habana's Gaudi and HPUs?
-    title: Conceptual Guides
   - sections:
     - local: package_reference/trainer
       title: Gaudi Trainer
     - local: package_reference/gaudi_config
       title: Gaudi Configuration
-    - local: package_reference/stable_diffusion_pipeline
-      title: Gaudi Stable Diffusion Pipeline
     - local: package_reference/distributed_runner
       title: Distributed Runner
     title: Reference
-  title: Optimum Habana
-  isExpanded: false
+  title: Optimum for Intel Gaudi
+  isExpanded: false