[None][infra] Cherry-pick #6128 and #6130 from main branch (#6151)

Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Signed-off-by: qqiao <qqiao@nvidia.com>
Co-authored-by: Emma Qiao <qqiao@nvidia.com>
This commit is contained in:
Yanchao Lu 2025-07-18 11:02:11 +08:00 committed by GitHub
parent 4d0bcbcb2d
commit eeca3ad084
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 41 additions and 5 deletions

22
.coderabbit.yaml Normal file
View File

@ -0,0 +1,22 @@
# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json
language: "en-US"
reviews:
auto_review:
drafts: true
base_branches: ["main", "release/.+"]
commit_status: false

View File

@ -1,17 +1,24 @@
@coderabbitai summary
# PR title
<!--
Please write the PR title by following this template:
Please write the PR title by following template:
[JIRA ticket/NVBugs ID/GitHub issue][fix/feat/doc/infra/...] \<summary of this PR\>
[JIRA ticket link/nvbug link/github issue link][fix/feat/doc/infra/...] \<summary of this PR\>
For example, assume I have a PR hope to support a new feature about cache manager of Jira TRTLLM-1000 ticket, it would be like
For example, assume I have a PR to support a new feature about cache manager for JIRA ticket TRTLLM-1000, it would be like:
[TRTLLM-1000][feat] Support a new feature about cache manager
Or I have a PR to fix a Llama3 accuracy issue:
[https://nvbugs/1234567][fix] Fix Llama3 accuracy issue
-->
## Description
<!--
Please explain the issue and the solution in short.
-->
## Test Coverage

View File

@ -309,6 +309,7 @@ def runLLMTestlistOnSlurm_MultiNodes(pipeline, platform, testList, config=VANILL
def llmSrcLocal = "${llmPath}/TensorRT-LLM/src"
def scriptRunNode = "${jobWorkspace}/slurm_run.sh"
def testListPathNode = "${jobWorkspace}/${testList}.txt"
def waivesListPathNode = "${jobWorkspace}/waives.txt"
def isAarch64 = config.contains("aarch64")
def pytestTestTimeout = "7200"
@ -325,6 +326,10 @@ def runLLMTestlistOnSlurm_MultiNodes(pipeline, platform, testList, config=VANILL
Utils.exec(pipeline, script: "chmod +x ${scriptRunLocalPath}", returnStdout: true)
Utils.exec(pipeline, script: "sshpass -p '${remote.passwd}' scp -r -p -oStrictHostKeyChecking=no ${scriptRunLocalPath} ${remote.user}@${remote.host}:${scriptRunNode}",)
// Upload waives.txt to Frontend node
def waivesListLocalPath = "${llmSrcLocal}/tests/integration/test_lists/waives.txt"
Utils.exec(pipeline, script: "sshpass -p '${remote.passwd}' scp -r -p -oStrictHostKeyChecking=no ${waivesListLocalPath} ${remote.user}@${remote.host}:${waivesListPathNode}",)
// Generate Test List and Upload to Frontend Node
def makoArgs = getMakoArgsFromStageName(stageName, true)
// TODO: currently the options will only be processed if the first
@ -362,6 +367,7 @@ def runLLMTestlistOnSlurm_MultiNodes(pipeline, platform, testList, config=VANILL
export stageName=$stageName
export testList=$testList
export testListPathNode=$testListPathNode
export waivesListPathNode=$waivesListPathNode
export pytestTestTimeout=$pytestTestTimeout
export splits=$splits
export splitId=$splitId

View File

@ -45,6 +45,7 @@ testCmdLines=(
"-v"
"--timeout=$pytestTestTimeout"
"--test-list=$testListPathNode"
"--waives-file=$waivesListPathNode"
"--rootdir $llmSrcNode/tests/integration/defs"
"--test-prefix=$stageName"
"--splits $splits"