test: update gpu test for llama3 (#204)

Signed-off-by: Sertac Ozercan <[email protected]>

.github/workflows/test-docker-gpu.yaml

@@ -47,8 +47,22 @@ jobs:
       - name: run test model
         run: docker run --name testmodel -d --rm -p 8080:8080 --gpus all testmodel:test
 
-      - name: run test
-        if: matrix.backend != 'mamba'
+      - name: run test (gguf)
+        if: matrix.backend == 'llama-cuda'
+        run: |
+          result=$(curl --fail --retry 10 --retry-all-errors http://127.0.0.1:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
+            "model": "llama-3-8b-chat",
+            "messages": [{"role": "user", "content": "explain kubernetes in a sentence"}]
+          }')
+          echo $result
+
+          choices=$(echo "$result" | jq '.choices')
+          if [ -z "$choices" ]; then
+            exit 1
+          fi
+
+      - name: run test (exl2/gptq)
+        if: matrix.backend == 'exllama2-gptq' || matrix.backend == 'exllama2-exl2'
         run: |
           result=$(curl --fail --retry 10 --retry-all-errors http://127.0.0.1:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
             "model": "llama-2-7b-chat",
@@ -61,7 +75,7 @@ jobs:
             exit 1
           fi
 
-      - name: run test
+      - name: run test (mamba)
         if: matrix.backend == 'mamba'
         run: |
           result=$(curl --fail --retry 10 --retry-all-errors http://127.0.0.1:8080/v1/chat/completions -H "Content-Type: application/json" -d '{