Upgrade TGI Gaudi version to v2.0.6 (#1088)

Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>

MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md

@@ -80,7 +80,7 @@ docker build --no-cache -t opea/retriever-multimodal-redis:latest --build-arg ht
 Build TGI Gaudi image
 
 ```bash
-docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5
+docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6
 ```
 
 Build lvm-tgi microservice image
@@ -118,7 +118,7 @@ Then run the command `docker images`, you will have the following 8 Docker Image
 
 1. `opea/dataprep-multimodal-redis:latest`
 2. `opea/lvm-tgi:latest`
-3. `ghcr.io/huggingface/tgi-gaudi:2.0.5`
+3. `ghcr.io/huggingface/tgi-gaudi:2.0.6`
 4. `opea/retriever-multimodal-redis:latest`
 5. `opea/embedding-multimodal:latest`
 6. `opea/embedding-multimodal-bridgetower:latest`

MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -69,7 +69,7 @@ services:
       INDEX_NAME: ${INDEX_NAME}
     restart: unless-stopped
   tgi-gaudi:
-    image: ghcr.io/huggingface/tgi-gaudi:2.0.5
+    image: ghcr.io/huggingface/tgi-gaudi:2.0.6
     container_name: tgi-llava-gaudi-server
     ports:
       - "8399:80"
@@ -84,6 +84,10 @@ services:
       PREFILL_BATCH_BUCKET_SIZE: 1
       BATCH_BUCKET_SIZE: 1
       MAX_BATCH_TOTAL_TOKENS: 4096
+      ENABLE_HPU_GRAPH: true
+      LIMIT_HPU_GRAPH: true
+      USE_FLASH_ATTENTION: true
+      FLASH_ATTENTION_RECOMPUTE: true
     runtime: habana
     cap_add:
       - SYS_NICE