replace bigdl-llm with ipex-llm

intel-analytics · Mar 26, 2024 · d91e489 · d91e489
1 parent c563b41
commit d91e489
Show file tree

Hide file tree

Showing 11 changed files with 101 additions and 2,571 deletions.
diff --git a/.github/actions/llm/convert-test/action.yml b/.github/actions/llm/convert-test/action.yml
@@ -1,5 +1,5 @@
-name: "BigDL-LLM convert tests"
-description: "BigDL-LLM convert test, including downloading original models"
+name: "IPEX-LLM convert tests"
+description: "IPEX-LLM convert test, including downloading original models"
 
 runs:
   using: "composite"

diff --git a/.github/actions/llm/example-test/action.yml b/.github/actions/llm/example-test/action.yml
@@ -1,5 +1,5 @@
-name: 'BigDL-LLM example tests'
-description: 'BigDL-LLM example tests'
+name: 'IPEX-LLM example tests'
+description: 'IPEX-LLM example tests'
 
 runs:
   using: "composite"

diff --git a/.github/actions/llm/setup-llm-env/action.yml b/.github/actions/llm/setup-llm-env/action.yml
@@ -1,5 +1,5 @@
-name: "Setup BigDL-LLM Env"
-description: "BigDL-LLM installation"
+name: "Setup IPEX-LLM Env"
+description: "IPEX-LLM installation"
 inputs:
   extra-dependency:
     description: "Name of extra dependencies filled in brackets"

diff --git a/.github/workflows/llm-harness-evaluation.yml b/.github/workflows/llm-harness-evaluation.yml
@@ -276,7 +276,7 @@ jobs:
       - name: Download FP16 results
         shell: bash
         run: |
-          wget https://raw.githubusercontent.com/intel-analytics/BigDL/main/python/llm/test/benchmark/harness/fp16.csv -O $ACC_FOLDER/../fp16.csv
+          wget https://raw.githubusercontent.com/intel-analytics/ipex-llm/main/python/llm/test/benchmark/harness/fp16.csv -O $ACC_FOLDER/../fp16.csv
           ls $ACC_FOLDER/..
 
       - name: Write to CSV

diff --git a/.github/workflows/llm-nightly-test.yml b/.github/workflows/llm-nightly-test.yml
@@ -83,7 +83,7 @@ jobs:
       - name: Download llm binary
         uses: ./.github/actions/llm/download-llm-binary
 
-      - name: Install BigDL-LLM
+      - name: Install IPEX-LLM
         uses: ./.github/actions/llm/setup-llm-env
 
       - name: Download original models & convert

diff --git a/.github/workflows/llm-ppl-evaluation.yml b/.github/workflows/llm-ppl-evaluation.yml
@@ -259,7 +259,7 @@ jobs:
       - name: Download fp16.results
         shell: bash
         run: |
-          wget https://raw.githubusercontent.com/intel-analytics/BigDL/main/python/llm/test/benchmark/perplexity/fp16.csv -O $ACC_FOLDER/../fp16.csv
+          wget https://raw.githubusercontent.com/intel-analytics/ipex-llm/main/python/llm/test/benchmark/perplexity/fp16.csv -O $ACC_FOLDER/../fp16.csv
           ls $ACC_FOLDER/..
 
       - name: Write to CSV

diff --git a/.github/workflows/llm-whisper-evaluation.yml b/.github/workflows/llm-whisper-evaluation.yml
@@ -111,7 +111,7 @@ jobs:
           python -m pip install --upgrade librosa
           python -m pip install --upgrade jiwer
 
-      # please uncomment it and comment the "Install BigDL-LLM from Pypi" part for PR tests
+      # please uncomment it and comment the "Install IPEX-LLM from Pypi" part for PR tests
       - name: Download llm binary
         uses: ./.github/actions/llm/download-llm-binary
 
@@ -120,10 +120,10 @@ jobs:
         with:
           extra-dependency: "xpu_2.1"
 
-      # - name: Install BigDL-LLM from Pypi
+      # - name: Install IPEX-LLM from Pypi
       #   shell: bash
       #   run: |
-      #     pip install --pre --upgrade bigdl-llm[xpu] -f https://developer.intel.com/ipex-whl-stable-xpu
+      #     pip install --pre --upgrade ipex-llm[xpu] -f https://developer.intel.com/ipex-whl-stable-xpu
 
       # - name: Test installed xpu version
       #   shell: bash

diff --git a/.github/workflows/llm_tests_for_stable_version_on_spr.yml b/.github/workflows/llm_tests_for_stable_version_on_spr.yml
@@ -67,7 +67,7 @@ jobs:
           cd python/llm/dev/benchmark/all-in-one
           export http_proxy=${HTTP_PROXY}
           export https_proxy=${HTTPS_PROXY}
-          source bigdl-llm-init -t
+          source ipex-llm-init -t
           export OMP_NUM_THREADS=48
           # hide time info
           sed -i 's/str(end - st)/"xxxxxx"/g' run.py
@@ -125,7 +125,7 @@ jobs:
           cd python/llm/dev/benchmark/all-in-one
           export http_proxy=${HTTP_PROXY}
           export https_proxy=${HTTPS_PROXY}
-          source bigdl-llm-init -t
+          source ipex-llm-init -t
           export OMP_NUM_THREADS=48
           # hide time info
           sed -i 's/str(end - st)/"xxxxxx"/g' run-stress-test.py

diff --git a/.github/workflows/llm_unit_tests.yml b/.github/workflows/llm_unit_tests.yml
@@ -273,7 +273,7 @@ jobs:
       - name: Download llm binary
         uses: ./.github/actions/llm/download-llm-binary
 
-      - name: Install BigDL-LLM for xpu
+      - name: Install IPEX-LLM for xpu
         uses: ./.github/actions/llm/setup-llm-env
         with:
           extra-dependency: "xpu_${{ matrix.pytorch-version }}"
@@ -392,10 +392,10 @@ jobs:
           pip install llama-index-readers-file llama-index-vector-stores-postgres llama-index-embeddings-huggingface
           # Specific oneapi position on arc ut test machines
           if [[ '${{ matrix.pytorch-version }}' == '2.1' ]]; then
-            pip install --pre --upgrade bigdl-llm[xpu] -f https://developer.intel.com/ipex-whl-stable-xpu
+            pip install --pre --upgrade ipex-llm[xpu] -f https://developer.intel.com/ipex-whl-stable-xpu
             source /opt/intel/oneapi/setvars.sh
           elif [[ '${{ matrix.pytorch-version }}' == '2.0' ]]; then
-            pip install --pre --upgrade bigdl-llm[xpu_2.0] -f https://developer.intel.com/ipex-whl-stable-xpu
+            pip install --pre --upgrade ipex-llm[xpu_2.0] -f https://developer.intel.com/ipex-whl-stable-xpu
             source /home/arda/intel/oneapi/setvars.sh
           fi
           bash python/llm/test/run-llm-llamaindex-tests-gpu.sh