1 Release published by 1 person

• v1.4 Generative AI Examples v1.4 Release Notes

  published Aug 25, 2025

16 Pull requests merged by 8 people

• Bump @sveltejs/kit from 2.0.0 to 2.20.6 in /HybridRAG/ui/svelte

  #2212 merged Aug 25, 2025

• Bump svelte from 4.2.7 to 4.2.19 in /Translation/ui/svelte

  #2108 merged Aug 22, 2025

• Bump @sveltejs/kit from 2.0.0 to 2.20.6 in /Text2Image/ui/svelte

  #2214 merged Aug 22, 2025

• Update v1.4 Release Test Config

  #2220 merged Aug 22, 2025

• Bump llama-index-core from 0.12.37 to 0.12.41 in /EdgeCraftRAG/edgecraftrag

  #2142 merged Aug 22, 2025

• Sync helm charts values with GenAIInfra

  #2219 merged Aug 22, 2025

• CI/CD enhance

  #2216 merged Aug 22, 2025

• Remove "VLLM_CPU_OMP_THREADS_BIND:all" from Xeon compose files

  #2213 merged Aug 21, 2025

• Bump requests from 2.28.1 to 2.32.4 in /WorkflowExecAgent/tests/example_workflow

  #2110 merged Aug 20, 2025

• Bump llama-index from 0.12.36 to 0.12.41 in /EdgeCraftRAG/edgecraftrag

  #2141 merged Aug 20, 2025

• Bump @sveltejs/kit from 2.0.0 to 2.20.6 in /Translation/ui/svelte

  #2109 merged Aug 20, 2025

• add deep research agent benchmark script.

  #2135 merged Aug 20, 2025

• Update vLLM version to v0.10.0

  #2205 merged Aug 19, 2025

• Support mutli-model test for weekly oneclick

  #2204 merged Aug 19, 2025

• Enable Xeon optimizations like Tensor Parallel and AMX from vLLM 0.10.0

  #2106 merged Aug 18, 2025

• fix image build bug 1781

  #2200 merged Aug 18, 2025

6 Pull requests opened by 4 people

• dynamic model switch

  #2211 opened Aug 20, 2025

• Fix build fail for EdgeCraftRAG.

  #2218 opened Aug 22, 2025

• Bump svelte from 4.2.7 to 4.2.19 in /HybridRAG/ui/svelte

  #2221 opened Aug 22, 2025

• Bump @sveltejs/kit from 2.0.0 to 2.20.6 in /AudioQnA/ui/svelte

  #2223 opened Aug 25, 2025

• Bump @sveltejs/kit from 2.0.0 to 2.20.6 in /DocSum/ui/svelte

  #2224 opened Aug 25, 2025

• Fix UI sending chat history to backend

  #2225 opened Aug 25, 2025

6 Issues closed by 4 people

• [Bug] DocSum megaservice test timeout

  #2215 closed Aug 25, 2025

• [Bug] Running AgentQnA example on Gaudi3 gives Segmentation Fault error

  #2016 closed Aug 24, 2025

• ChatQNA containers failing at launch

  #2128 closed Aug 24, 2025

• [Feature] Replace WEBUI for AgentQnA example

  #2009 closed Aug 22, 2025

• [Feature] Enable remote inference endpoints for examples

  #1973 closed Aug 19, 2025

• [Feature] enable AMX support for vLLM on GNR/EMR/SPR

  #2045 closed Aug 18, 2025

3 Issues opened by 3 people

• [Bug] HybridRAG UT run fail on Gaudi

  #2222 opened Aug 22, 2025

• [Bug]

  #2209 opened Aug 20, 2025

• [Bug] Containers are run as privileged (security issue)

  #2207 opened Aug 18, 2025

8 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• add test script

  #2199 commented on Aug 20, 2025 • 19 new comments

• Exceptions in application logs with larger or larger number of requests

  #469 commented on Aug 19, 2025 • 0 new comments

• [Feature] Add remote inference endpoint support in CI/CD

  #2005 commented on Aug 19, 2025 • 0 new comments

• [Feature] Remote Inference Endpoints Support

  #1972 commented on Aug 19, 2025 • 0 new comments

• [Bug] AudioQnA failed with multilang on xeon after vllm version update to v0.9.0.1

  #2048 commented on Aug 22, 2025 • 0 new comments

• ChatQnA - Adding files to deploy an application in the K8S environment using Helm

  #1759 commented on Aug 20, 2025 • 0 new comments

• Update vLLM-fork version to v0.8.5.post1+Gaudi-1.21.3

  #1922 commented on Aug 25, 2025 • 0 new comments

• ChatQnA Example with OpenAI-Compatible Endpoint

  #2091 commented on Aug 20, 2025 • 0 new comments