amitz-nv · amitz-nv · Jul 17, 2025 · Jul 17, 2025 · Jul 17, 2025 · Jul 17, 2025
diff --git a/.clangd b/.clangd
@@ -29,7 +29,7 @@ CompileFlags:
 # Tweak the clangd parse settings for all files
 CompileFlags:
   Compiler: clang++
-  CompilationDatabase: .
+  CompilationDatabase: cpp/build
   Add:
     # report all errors
     - "-ferror-limit=0"

diff --git a/.coderabbit.yaml b/.coderabbit.yaml
@@ -14,9 +14,26 @@
 # limitations under the License.
 
 # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json
+# https://docs.coderabbit.ai/getting-started/configure-coderabbit/
+# In PR, comment "@coderabbitai configuration" to get the full config including defaults
 language: "en-US"
 reviews:
+  profile: chill
+  auto_title_placeholder: '@coderabbitai title'
+  auto_title_instructions: 'Should follow the format: "[fix/feat/doc/infra/...] \<summary of this PR\>". Keep it concise.'
+  commit_status: false
+  collapse_walkthrough: true
+  assess_linked_issues: true
+  related_issues: true
+  related_prs: true
+  suggested_labels: true
+  suggested_reviewers: true
+  auto_assign_reviewers: true
+  poem: false
   auto_review:
     drafts: true
     base_branches: ["main", "release/.+"]
-  commit_status: false
+knowledge_base:
+  code_guidelines:
+    enabled: true
+    filePatterns: ["**/CODING_GUIDELINES.md"]
diff --git a/.github/pull_request_template.md b/.github/pull_request_template.md
@@ -38,29 +38,40 @@ See details below for each supported subcommand.
 
 <details>
 
-`run  [--disable-fail-fast --skip-test --stage-list "A10-1, xxx" --gpu-type "A30, H100_PCIe" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-[Post-Merge]-1, xxx"]`
+`run  [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]`
 
 Launch build/test pipelines. All previously running jobs will be killed.
 
+`--reuse-test (optional)pipeline-id ` *(OPTIONAL)* : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.
+
+`--disable-reuse-test ` *(OPTIONAL)* : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.
+
 `--disable-fail-fast ` *(OPTIONAL)* : Disable fail fast on build/tests/infra failures.
 
 `--skip-test ` *(OPTIONAL)* : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does **NOT** update GitHub check status.
 
-`--stage-list "A10-1, xxx"` *(OPTIONAL)* : Only run the specified test stages. Examples: "A10-1, xxx". Note: Does **NOT** update GitHub check status.
+`--stage-list "A10-PyTorch-1, xxx"` *(OPTIONAL)* : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does **NOT** update GitHub check status.
 
 `--gpu-type "A30, H100_PCIe"` *(OPTIONAL)* : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does **NOT** update GitHub check status.
 
+`--test-backend "pytorch, cpp"` *(OPTIONAL)* : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does **NOT** update GitHub pipeline status.
+
 `--only-multi-gpu-test ` *(OPTIONAL)* : Only run the multi-GPU tests. Note: Does **NOT** update GitHub check status.
 
 `--disable-multi-gpu-test ` *(OPTIONAL)* : Disable the multi-GPU tests. Note: Does **NOT** update GitHub check status.
 
-`--add-multi-gpu-test ` *(OPTIONAL)* : Force run the multi-GPU tests. Will also run L0 pre-merge pipeline.
+`--add-multi-gpu-test ` *(OPTIONAL)* : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.
 
 `--post-merge ` *(OPTIONAL)* : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.
 
-`--extra-stage "H100_PCIe-[Post-Merge]-1, xxx"` *(OPTIONAL)* : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-[Post-Merge]-1, xxx".
+`--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx"` *(OPTIONAL)* : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".
+
+`--detailed-log ` *(OPTIONAL)* : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.
+
+`--debug ` *(OPTIONAL)* : **Experimental feature**. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in the `stage-list` parameter to access the appropriate container environment. Note: Does **NOT** update GitHub check status.
 
-For guidance on mapping tests to stage names, see `docs/source/reference/ci-overview.md`.
+For guidance on mapping tests to stage names, see `docs/source/reference/ci-overview.md`
+and the `scripts/test_to_stage_mapping.py` helper.
 
 ### kill
 

diff --git a/.github/workflows/blossom-ci.yml b/.github/workflows/blossom-ci.yml
@@ -40,7 +40,7 @@ jobs:
         startsWith(github.event.comment.body, '/bot skip --comment') ||
         startsWith(github.event.comment.body, '/bot reuse-pipeline') ||
         startsWith(github.event.comment.body, '/bot kill')) && contains(
-        fromJson('["byshiue","chuangz0","funatiq","hypdeb","jdemouth-nvidia","joyang-nv","lowsfer","Tabrizian","yweng0828","Shixiaowei02","MartinMarciniszyn","schetlur-nv","dcampora","pcastonguay","Naveassaf","lfr-0531","nekorobov","PerkzZheng","kaiyux","nv-guomingz","LinPoly","thorjohnsen","jiahanc","latency1024","tburt-nv","zeroepoch","chzblych","niukuo","ZhanruiSunCh","EmmaQiaoCh","yiqingy0","achartier","suyoggupta","amukkara","mk-nvidia","QiJune","lucaslie","davidmlw","hlu1","nvzhou","syuoni","NVGaryJi","symphonylyh","hello-11","zongfeijing","Jackch-NV","jinyangyuan-nvidia","LarryXFly","crazydemo","jaedeok-nvidia","wm2012011492","rosenrodt","zhuoyao1012","xinhe-nv","Yuening-wa","Shunkangz","zhengd-nv","yibinl-nvidia","StanleySun639","KingsleyLiu-NV","kxdc","yingcanw","BestJuly","ChristinaZ","bobboli","xueweilnvidia","kunlunl","cherichy","lucifer1004","Autumn1998","litaotju","peaceh-nv","liji-nv","SimengLiu-nv","yuxianq","yechank-nvidia","vallis-neria","DylanChen-NV","Tracin","zhhuang-nv","ISEEKYAN","xupinjie","tongyuantongyu","laikhtewari","zhuolingwang","dominicshanshan","jershi425","shifangx","StudyingShao","Superjomn","dongjiyingdjy","guangyunh-nv","wili-65535","tiffany940107","DanBlanaru","mikeiovine","djns99","ruodil","xiaoweiw-nv","xuwchen","bashimao","yizhang-nv","hyukn","nvpohanh","yuki-666","juney-nvidia","barry-delaney","Kefeng-Duan","MinaHuai","yilin-void","jhaotingc","jmydurant","katec846","CarstyYou","Njuapp","Jie-Fang","nvbrantz","inocsin","ruoqianguo","chenfeiz0326","ming-wei","eopXD","longlee0622","dongfengy","georgeliu95","evezhier","rakib-hasan","shangz-ai","JyChang012","wangsiping1997","yuanjings-nvda","tomeras91","roikoren755","amirkl94","shaharmor98","danielafrimi","amitz-nv","hijkzzz","rzilberstein-nvidia","dc3671","hchings","yuhengxnv","dongxuy04","qiaoxj07","omera-nv","DomBrown","brb-nv","FrankD412","yuhsuan-t","Fridah-nv","a-mccarthy","HuiGao-NV","alexmsettle","meenchen","sugunav14","cjluo-nv","kyleliang-nv","chang-l","WeiHaocheng","qixiang-99","BatshevaBlack","ebarilanM","xmchen1987","lingjiew","heyuhhh","netanel-haber","jiefangz-nv","wyw1267","yunruis","sklevtsov-nvidia","jgangani","pamelap-nvidia","ixlmar","GalSha","Dido0o0","rabiel","nvzhihanj","milesial","fzmu727","zackyoray","RoeyAzran1992","viraatc","v-shobhit","yuanjingx87","uchihatmtkinu","nvrohanv","vegaluisjose","qsang-nv","ChunhuanLin","timlee0212","venkywonka","zbpatel","tijyojwad","shyeh25","zihaok","nv-yilinf","ttyio","farazkh80","yuantailing","JennyLiu-nv","moraxu","IzzyPutterman","nvchenghaoz","nvxuanyuc","poweiw","stnie","zhanga5","nzmora-nvidia","greg-kwasniewski1","linda-stadter","Tom-Zheng","vanshilshah97","ixlmar","MatthiasKohl","Wanli-Jiang", "arekay", "davidclark-nv", "2ez4bz", "tcherckez-nvidia", "MrGeva", "galagam", "limin2021", "dhansen-nvidia","talorabr","kanghui0204","wu6u3tw","hvagadia","xavier-nvidia","raayandhar","dbari","nvjullin","elvischenv","zhenhuaw-me","weireweire","yifeizhang-c","jiaganc","ziyixiong-nv","FelixXidddd","JunyiXu-nv","bo-nv","zerollzeng","RayenTian","ameynaik-hub"]'),
+        fromJson('["byshiue","chuangz0","funatiq","hypdeb","jdemouth-nvidia","joyang-nv","lowsfer","Tabrizian","yweng0828","Shixiaowei02","MartinMarciniszyn","schetlur-nv","dcampora","pcastonguay","Naveassaf","lfr-0531","nekorobov","PerkzZheng","kaiyux","nv-guomingz","LinPoly","thorjohnsen","jiahanc","latency1024","tburt-nv","zeroepoch","chzblych","niukuo","ZhanruiSunCh","EmmaQiaoCh","yiqingy0","achartier","suyoggupta","amukkara","mk-nvidia","QiJune","lucaslie","davidmlw","hlu1","nvzhou","syuoni","NVGaryJi","symphonylyh","hello-11","zongfeijing","Jackch-NV","jinyangyuan-nvidia","LarryXFly","crazydemo","jaedeok-nvidia","wm2012011492","rosenrodt","zhuoyao1012","xinhe-nv","Yuening-wa","Shunkangz","zhengd-nv","yibinl-nvidia","StanleySun639","KingsleyLiu-NV","kxdc","yingcanw","BestJuly","ChristinaZ","bobboli","xueweilnvidia","kunlunl","cherichy","lucifer1004","Autumn1998","litaotju","peaceh-nv","liji-nv","SimengLiu-nv","yuxianq","yechank-nvidia","vallis-neria","DylanChen-NV","Tracin","zhhuang-nv","ISEEKYAN","xupinjie","tongyuantongyu","laikhtewari","zhuolingwang","dominicshanshan","jershi425","shifangx","StudyingShao","Superjomn","dongjiyingdjy","guangyunh-nv","wili-65535","tiffany940107","DanBlanaru","mikeiovine","djns99","ruodil","xiaoweiw-nv","xuwchen","bashimao","yizhang-nv","hyukn","nvpohanh","yuki-666","juney-nvidia","barry-delaney","Kefeng-Duan","MinaHuai","yilin-void","jhaotingc","jmydurant","katec846","CarstyYou","Njuapp","Jie-Fang","nvbrantz","inocsin","ruoqianguo","chenfeiz0326","ming-wei","eopXD","longlee0622","dongfengy","georgeliu95","evezhier","rakib-hasan","shangz-ai","JyChang012","wangsiping1997","yuanjings-nvda","tomeras91","roikoren755","amirkl94","shaharmor98","danielafrimi","amitz-nv","hijkzzz","rzilberstein-nvidia","dc3671","hchings","yuhengxnv","dongxuy04","qiaoxj07","omera-nv","DomBrown","brb-nv","FrankD412","yuhsuan-t","Fridah-nv","a-mccarthy","HuiGao-NV","alexmsettle","meenchen","sugunav14","cjluo-nv","kyleliang-nv","chang-l","WeiHaocheng","qixiang-99","BatshevaBlack","ebarilanM","xmchen1987","lingjiew","heyuhhh","netanel-haber","jiefangz-nv","wyw1267","yunruis","sklevtsov-nvidia","jgangani","pamelap-nvidia","ixlmar","GalSha","Dido0o0","rabiel","nvzhihanj","milesial","fzmu727","zackyoray","RoeyAzran1992","viraatc","v-shobhit","yuanjingx87","uchihatmtkinu","nvrohanv","vegaluisjose","qsang-nv","ChunhuanLin","timlee0212","venkywonka","zbpatel","tijyojwad","shyeh25","zihaok","nv-yilinf","ttyio","farazkh80","yuantailing","JennyLiu-nv","moraxu","IzzyPutterman","nvchenghaoz","nvxuanyuc","poweiw","stnie","zhanga5","nzmora-nvidia","greg-kwasniewski1","linda-stadter","Tom-Zheng","vanshilshah97","ixlmar","MatthiasKohl","Wanli-Jiang", "arekay", "davidclark-nv", "2ez4bz", "tcherckez-nvidia", "MrGeva", "galagam", "limin2021", "dhansen-nvidia","talorabr","kanghui0204","wu6u3tw","hvagadia","xavier-nvidia","raayandhar","dbari","nvjullin","elvischenv","zhenhuaw-me","weireweire","yifeizhang-c","jiaganc","ziyixiong-nv","FelixXidddd","JunyiXu-nv","bo-nv","zerollzeng","RayenTian","ameynaik-hub","raymochen","shuyixiong","johncalesp","leslie-fang25","reasonsolo","zhou-yuxin","vadiklyutiy","yali-arch","NVShreyas","h-guo18","pengbowang-nv"]'),
         github.actor)
     steps:
       - name: Check if comment is issued by authorized person

diff --git a/.github/workflows/bot-command.yml b/.github/workflows/bot-command.yml
@@ -46,17 +46,22 @@ jobs:
             "Run `/bot [-h|--help]` to print this help message.\n\n" +
             "See details below for each supported subcommand.\n\n" +
             "<details>\n\n" +
-            "`run  [--disable-fail-fast --skip-test --stage-list \"A10-1, xxx\" --gpu-type \"A30, H100_PCIe\" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage \"H100_PCIe-[Post-Merge]-1, xxx\"]`\n\n" +
+            "`run  [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list \"A10-PyTorch-1, xxx\" --gpu-type \"A30, H100_PCIe\" --test-backend \"pytorch, cpp\" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage \"H100_PCIe-TensorRT-Post-Merge-1, xxx\" --detailed-log --debug(experimental)]`\n\n" +
             "Launch build/test pipelines. All previously running jobs will be killed.\n\n" +
+            "`--reuse-test (optional)pipeline-id ` *(OPTIONAL)* : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.\n\n" +
+            "`--disable-reuse-test ` *(OPTIONAL)* : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.\n\n" +
             "`--disable-fail-fast ` *(OPTIONAL)* : Disable fail fast on build/tests/infra failures.\n\n" +
             "`--skip-test ` *(OPTIONAL)* : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does **NOT** update GitHub check status.\n\n" +
-            "`--stage-list \"A10-1, xxx\"` *(OPTIONAL)* : Only run the specified test stages. Examples: \"A10-1, xxx\". Note: Does **NOT** update GitHub check status.\n\n" +
+            "`--stage-list \"A10-PyTorch-1, xxx\"` *(OPTIONAL)* : Only run the specified test stages. Examples: \"A10-PyTorch-1, xxx\". Note: Does **NOT** update GitHub check status.\n\n" +
             "`--gpu-type \"A30, H100_PCIe\"` *(OPTIONAL)* : Only run the test stages on the specified GPU types. Examples: \"A30, H100_PCIe\". Note: Does **NOT** update GitHub check status.\n\n" +
+            "`--test-backend \"pytorch, cpp\"` *(OPTIONAL)* : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: \"pytorch, cpp\" (does not run test stages with tensorrt or triton backend). Note: Does **NOT** update GitHub pipeline status.\n\n" +
             "`--only-multi-gpu-test ` *(OPTIONAL)* : Only run the multi-GPU tests. Note: Does **NOT** update GitHub check status.\n\n" +
             "`--disable-multi-gpu-test ` *(OPTIONAL)* : Disable the multi-GPU tests. Note: Does **NOT** update GitHub check status.\n\n" +
-            "`--add-multi-gpu-test ` *(OPTIONAL)* : Force run the multi-GPU tests. Will also run L0 pre-merge pipeline.\n\n" +
+            "`--add-multi-gpu-test ` *(OPTIONAL)* : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.\n\n" +
             "`--post-merge ` *(OPTIONAL)* : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.\n\n" +
-            "`--extra-stage \"H100_PCIe-[Post-Merge]-1, xxx\"` *(OPTIONAL)* : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage \"H100_PCIe-[Post-Merge]-1, xxx\".\n\n" +
+            "`--extra-stage \"H100_PCIe-TensorRT-Post-Merge-1, xxx\"` *(OPTIONAL)* : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage \"H100_PCIe-TensorRT-Post-Merge-1, xxx\".\n\n" +
+            "`--detailed-log ` *(OPTIONAL)* : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.\n\n" +
+            "`--debug ` *(OPTIONAL)* : **Experimental feature**. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in the `stage-list` parameter to access the appropriate container environment. Note: Does **NOT** update GitHub check status.\n\n" +
             "### kill\n\n" +
             "`kill  `\n\n" +
             "Kill all running builds associated with pull request.\n\n" +

diff --git a/.github/workflows/label_issue.yml b/.github/workflows/label_issue.yml
@@ -0,0 +1,47 @@
+name: Label New Issues
+
+on:
+  issues:
+    types: [opened]
+
+permissions:
+  issues: write
+  contents: read
+
+jobs:
+  label-issue:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout private action repository
+        uses: actions/checkout@v4
+        with:
+          repository: poweiw/goggles_action
+          path: ./.github/actions/goggles_action # local path to store the action
+          token: ${{ secrets.GOGGLES_ACTION_REPO_TOKEN}} # token to access poweiw/goggles_action
+          ref: v1.2.1
+
+      - name: AI Label Issue
+        uses: ./.github/actions/goggles_action/actions/llm_label
+        with:
+          ACTION_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          LLM_MODEL_NAME: ${{ secrets.GOGGLES_LLM_MODEL_NAME }}
+          LLM_TOKEN_SERVER_URL: ${{ secrets.GOGGLES_LLM_TOKEN_SERVER_URL }}
+          LLM_TOKEN_CLIENT_ID: ${{ secrets.GOGGLES_LLM_TOKEN_CLIENT_ID }}
+          LLM_TOKEN_CLIENT_SECRET: ${{ secrets.GOGGLES_LLM_TOKEN_CLIENT_SECRET }}
+          LLM_GENERATE_URL: ${{ secrets.GOGGLES_LLM_GENERATE_URL }}
+          LLM_TOKEN_SCOPE: ${{ secrets.GOGGLES_LLM_TOKEN_SCOPE }}
+          REPO_OWNER: ${{ github.repository_owner }}
+          REPO_NAME: ${{ github.event.repository.name }}
+          ISSUE_NUMBER: ${{ github.event.issue.number }}
+          ISSUE_TITLE: ${{ github.event.issue.title }}
+          ISSUE_BODY: ${{ github.event.issue.body }}
+          GITHUB_API_URL: ${{ github.api_url }}
+          ACTIONS_STEP_VERBOSE: false
+          EXCLUDED_LABELS: "bug,Community want to contribute,Community Engagement,duplicate,help wanted,Investigating,need more info,question,roadmap,stale,waiting for feedback,wontfix"
+          LLM_SYSTEM_PROMPT: |
+            You are an expert GitHub issue labeler. Your task is to analyze the provided issue title, issue body, and a list of available labels with their descriptions.
+            Based on this information, select the single most appropriate label from the list that best captures the primary issue or request.
+            Prefer selecting only one label that represents the main topic or problem. Only suggest multiple labels if the issue genuinely spans multiple distinct areas that are equally important.
+            Respond with ONLY the chosen label name (e.g., 'bug', 'feature-request') or comma-separated names if multiple are truly needed.
+            If no labels seem appropriate, respond with 'NONE'.
+            Do not add any other text, explanation, or markdown formatting.