Merge branch 'main' into dev/kpietkun/sleep_mode

Author: Kacper-Pietkun

.cd/README.md

@@ -7,9 +7,9 @@ images and Docker Compose, with support for custom runtime parameters and
 benchmarking.
 
 Detailed Quick Start procedures are available in the `docs` folder:
-- [Basic Quick Start Guide](../docs/getting_started/quickstart/quickstart.md)
-- [Advanced Configuration Options](../docs/getting_started/quickstart/quickstart_configuration.md)
-- [Executing Inference](../docs/getting_started/quickstart/quickstart_inference.md)
+- [Basic Quick Start Guide](https://vllm-gaudi.readthedocs.io/en/latest/getting_started/quickstart/quickstart.html)
+- [Advanced Configuration Options](https://vllm-gaudi.readthedocs.io/en/latest/getting_started/quickstart/quickstart_configuration.html)
+- [Executing Inference](https://vllm-gaudi.readthedocs.io/en/latest/getting_started/quickstart/quickstart_inference.html)
 
 If you prefer to build vLLM Hardware Plugin for Intel Gaudi from source or with a custom
-Dockerfile, refer to the [Installation](../docs/getting_started/installation.md) guide.
+Dockerfile, refer to the [Installation](https://vllm-gaudi.readthedocs.io/en/latest/getting_started/installation.html) guide.

.cd/benchmark/benchmark_defaults.yaml

@@ -14,6 +14,7 @@ model_text:
     - Qwen/Qwen2.5-32B-Instruct
     - Qwen/Qwen2.5-72B-Instruct
     - Qwen/Qwen2.5-7B-Instruct
+    - Qwen/Qwen3-0.6B
     - ibm-granite/granite-8b-code-instruct-4k
     - ibm-granite/granite-20b-code-instruct-8k
   DATASET: /workspace/vllm-project/benchmarks/sonnet.txt

.cd/benchmark/benchmark_scenarios_text.yaml

@@ -41,6 +41,9 @@ qwen25_72b_instruct:
 qwen25_7b_instruct:
   MODEL: Qwen/Qwen2.5-7B-Instruct
 
+Qwen/Qwen3-0.6B:
+  MODEL: Qwen/Qwen3-0.6B
+
 granite_8b_code_instruct_4k:
   MODEL: ibm-granite/granite-8b-code-instruct-4k
 

.cd/docker-compose.yml

@@ -43,5 +43,5 @@ services:
     env_file:
       - ./benchmark/benchmark_user.env
     volumes:
-      - ./logs:/root/scripts/logs
+      - /tmp/logs:/root/scripts/logs
     command: ["benchmark", "--config-file", "${VLLM_BENCHMARK_CONFIG_FILE}", "--config-name", "${VLLM_BENCHMARK_CONFIG_NAME}"]

.cd/server/settings_vllm.csv

@@ -16,3 +16,4 @@ Qwen/Qwen2.5-7B-Instruct,1,4352,128,2,15231233024,2,2,14.18519115,0,10,5,128,1,3
 ibm-granite/granite-8b-code-instruct-4k,1,4096,128,2,21474836480,2,2,20,0,10,8,128,1,32,1,32,128,256,1,128,256,1,36,4096,8,32,2,32768,1,FALSE,FALSE,2048,FALSE,TRUE,TRUE,1,0
 ibm-granite/granite-20b-code-instruct-8k,1,4352,128,2,40133986304,2,2,37.37,0,10,4,128,1,32,1,32,128,256,1,128,256,1,52,6144,1,48,2,65536,1,FALSE,FALSE,2048,FALSE,TRUE,TRUE,1,0
 Qwen/Qwen2.5-VL-7B-Instruct,1,8448,128,2,15231233024,2,2,14.18519115,0,12,4,128,1,32,1,32,128,256,1,128,256,1,28,3584,4,28,2,32768,1,FALSE,FALSE,2048,FALSE,FALSE,FALSE,1,0
+Qwen/Qwen3-0.6B,1,4352,128,2,1.61E+09,2,2,1.5,0,10,5,128,1,32,1,32,128,256,1,128,256,1,28,1024,8,16,2,32768,1,FALSE,FALSE,2048,FALSE,TRUE,TRUE,1,0

.cd/templates/template_vllm_benchmark.sh

@@ -35,4 +35,6 @@ vllm bench serve \
                 --metric-percentiles 90 \
                 --ignore-eos \
                 --trust-remote-code \
-2>&1 | tee -a logs/perftest_inp${INPUT_TOK}_out${OUTPUT_TOK}_user${CONCURRENT_REQ}.log
+                --save-result \
+                --result-dir logs \
+                --result-filename summary_inp${INPUT_TOK}_out${OUTPUT_TOK}_user${CONCURRENT_REQ}.json 2>&1 | tee -a logs/summary_inp${INPUT_TOK}_out${OUTPUT_TOK}_user${CONCURRENT_REQ}.log #save results to logs on a host

.github/workflows/create-release-branch.yaml

@@ -154,7 +154,7 @@ jobs:
             --build-arg VLLM_COMMIT_ARG=${{ needs.prepare-release-branch.outputs.commit_id }} \
             -t hpu-plugin-v1-${{ needs.prepare-release-branch.outputs.tag_name }} \
             -f - . <<EOF
-          FROM vault.habana.ai/gaudi-docker/1.22.0/ubuntu24.04/habanalabs/pytorch-installer-2.7.1:latest
+          FROM vault.habana.ai/gaudi-docker/1.22.2/ubuntu24.04/habanalabs/pytorch-installer-2.7.1:latest
 
           COPY ./ /workspace/vllm-gaudi
           WORKDIR /workspace

.github/workflows/hourly-ci.yaml

@@ -89,7 +89,7 @@ jobs:
         run: |
           echo "Attempting to build Docker image..."
           docker build --no-cache -t hpu-plugin-v1-test-env-hourly-ci -f - . <<EOF
-          FROM vault.habana.ai/gaudi-docker/1.22.0/ubuntu24.04/habanalabs/pytorch-installer-2.7.1:latest
+          FROM vault.habana.ai/gaudi-docker/1.22.2/ubuntu24.04/habanalabs/pytorch-installer-2.7.1:latest
 
           COPY ./ /workspace/vllm-gaudi
           WORKDIR /workspace

.github/workflows/pre-merge.yaml

@@ -297,7 +297,7 @@ jobs:
             --build-arg VLLM_COMMIT_ARG=${{ env.TEST_VLLM_COMMIT }} \
             -t hpu-plugin-v1-test-env-pre-merge-${{ github.event.pull_request.head.sha }} \
             -f - . <<EOF
-          FROM vault.habana.ai/gaudi-docker/1.22.0/ubuntu24.04/habanalabs/pytorch-installer-2.7.1:latest
+          FROM vault.habana.ai/gaudi-docker/1.22.2/ubuntu24.04/habanalabs/pytorch-installer-2.7.1:latest
 
           ARG VLLM_COMMIT_ARG
 

README.md

@@ -15,7 +15,7 @@ vLLM Hardware Plugin for Intel® Gaudi®
 ---
 *Latest News* 🔥
 
-- [2025/11] The 0.10.2 release introduces the production-ready version of the vLLM Hardware Plugin for Intel® Gaudi® v1.23.0. The plugin is an alternative to the [vLLM fork](https://github.com/HabanaAI/vllm-fork), which reaches end of life with this release and will be deprecated in v1.24.0, remaining functional only for legacy use cases. We strongly encourage all fork users to begin planning their migration to the plugin. For more information about this release, see the [Release Notes](docs/release_notes.md).
+- [2025/11] The 0.11.2 release introduces the production-ready version of the vLLM Hardware Plugin for Intel® Gaudi® v1.22.2. The plugin is an alternative to the [vLLM fork](https://github.com/HabanaAI/vllm-fork), which reaches end of life with this release and will be deprecated in v1.24.0, remaining functional only for legacy use cases. We strongly encourage all fork users to begin planning their migration to the plugin. For more information about this release, see the [Release Notes](docs/release_notes.md).
 - [2025/06] We introduced an early developer preview of the vLLM Hardware Plugin for Intel® Gaudi®, which is not yet intended for general use.
 
 ---
@@ -67,7 +67,4 @@ We welcome and value any contributions and collaborations.
 
 <!-- --8<-- [start:contact-us] -->
 - For technical questions and feature requests, please use GitHub [Issues](https://github.com/vllm-project/vllm-gaudi/issues).
-- For discussing with fellow users, please use the [vLLM Forum](https://discuss.vllm.ai).
-- For coordinating contributions and development, please use [Slack](https://slack.vllm.ai).
-- For security disclosures, please use GitHub's [Security Advisories](https://github.com/vllm-project/vllm/security/advisories) feature.
 <!-- --8<-- [end:contact-us] -->