mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
* [Infra][TRTLLM-4063] - Branch out for the TRT-LLM v0.18.0 release Signed-off-by: Zhanrui Sun <zhanruis@nvidia.com> (cherry picked from commit de90312020e51c22ba5e75b3502c7ee90c059265) * [Infra][TRTLLM-3652] - Update dependencies to TRT 10.9 / CUDA 12.8.1 / DLFW 25.03(Internal) Signed-off-by: Yiqing Yan <yiqingy@nvidia.com> (cherry picked from commit 58db1340ef7db22f1910f878d220a92be5b830d1) * [None][Doc] - Update docs for v0.18.0 Signed-off-by: Yanchao Lu <yanchaol@nvidia.com> (cherry picked from commit d23e75bc95619ce3b116213d55319272888e0c88) * [Infra] - Fix or WAR issues in the package sanity check stages Signed-off-by: Yanchao Lu <yanchaol@nvidia.com> (cherry picked from commit e874e2b127515c52ba10c8df1cc2631627f74ffe) * [https://nvbugs/5173454] [https://nvbugs/5173432] [https://nvbugs/5175863] fix chatglm tokenizer and tmp model path Signed-off-by: Yuki Huang <yukih@nvidia.com> (cherry picked from commit 731811d4e182d70a66193d646152cb71dfafe83a) * cherry-pick 'test: Updat cluster and multi node test lists and trtllm-bench' test to fix perf drop issue Signed-off-by: Ruodi Lu <ruodil@nvidia.com> (cherry picked from commit 5214616283fbc15ae98871a1d84c78d8e1f2e6e8) * Revert "Merge branch 'user/yukih/fix_5173454_5173432' into 'release/0.18'" Signed-off-by: Yanchao Lu <yanchaol@nvidia.com> (cherry picked from commit 8d34831cb2b81ee2dfa8021b68e7158b33789a5f) * [Infra]Restrict setuptools version to avoid sasb pip install issue Signed-off-by: Emma Qiao <qqiao@nvidia.com> (cherry picked from commit 1e60ad29e0dafec0e295bedb5d89b716a02a707c) * [https://nvbugs/5173454] [https://nvbugs/5173432] [https://nvbugs/5175863] fix chatglm tokenizer and tmp model path Signed-off-by: Yuki Huang <yukih@nvidia.com> (cherry picked from commit 3ed8164e5bfea1d5aa2039b5408439fd6cf59dac) * WAR for bug 5173448 Signed-off-by: Thor Johnsen <tjohnsen@nvidia.com> (cherry picked from commit b6528b2ba15322b6c6a4c81a8b74c04d4973de4f) * [Infra][TRTLLM-3652] - Update dependencies to CUDA 12.8.1 / DLFW 25.03 Signed-off-by: Yiqing Yan <yiqingy@nvidia.com> (cherry picked from commit 6560983d132d9d257ee15849664eb055e94adaa9) * [Docs] - Doc changes for v0.18.0 Signed-off-by: Yanchao Lu <yanchaol@nvidia.com> (cherry picked from commit 26769b61218a947c8f9d070f73b63d576fcc20c4) * [Doc] - Doc change for v0.18.0 Signed-off-by: Yanchao Lu <yanchaol@nvidia.com> (cherry picked from commit 4b3b5ed6bfbc2300e3775fe75456083faad7b235) * [Infra] update version to 0.18.1 Signed-off-by: Zhanrui Sun <zhanruis@nvidia.com> (cherry picked from commit 59e8326c75639275837d34de8e140358737a3365) * Add back nemotron file. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Fix recurrentgemma reqs. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Adding WAR for bug 5173448. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Formatting. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Remove duplicated file. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Update examples/prompt_lookup/requirements.txt Co-authored-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com> Signed-off-by: Daniel Cámpora <961215+dcampora@users.noreply.github.com> * Remove glm-4-9b from model dir in chatglm test. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Remove indent change. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Apply suggestions from code review Co-authored-by: Yanchao Lu <yanchaol@nvidia.com> Signed-off-by: Daniel Cámpora <961215+dcampora@users.noreply.github.com> * Apply suggestions from code review Co-authored-by: Yanchao Lu <yanchaol@nvidia.com> Signed-off-by: Daniel Cámpora <961215+dcampora@users.noreply.github.com> * Revert changes on l0_test.groovy. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Update dev images Co-authored-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com> Signed-off-by: Yanchao Lu <yanchaol@nvidia.com> * Remove duplicated import. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Fix custom op Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com> * Fix flashinfer & vanilla backend Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com> * Skip problematic case. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Skip problematic test_moe_w4a8_1_14336_4096_8_bfloat16_True_False case. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> --------- Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> Signed-off-by: Daniel Cámpora <961215+dcampora@users.noreply.github.com> Signed-off-by: Yanchao Lu <yanchaol@nvidia.com> Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com> Co-authored-by: Zhanrui Sun <zhanruis@nvidia.com> Co-authored-by: Yiqing Yan <yiqingy@nvidia.com> Co-authored-by: Yanchao Lu <yanchaol@nvidia.com> Co-authored-by: Yuki Huang <yukih@nvidia.com> Co-authored-by: Ruodi Lu <ruodil@nvidia.com> Co-authored-by: Emma Qiao <qqiao@nvidia.com> Co-authored-by: Thor Johnsen <tjohnsen@nvidia.com> Co-authored-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com> Co-authored-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com> Co-authored-by: Tao Li @ NVIDIA <tali@nvidia.com>
145 lines
5.5 KiB
Groovy
145 lines
5.5 KiB
Groovy
|
|
import java.lang.InterruptedException
|
|
|
|
DOCKER_IMAGE = "urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.03-py3-x86_64-ubuntu24.04-trt10.9.0.34-skip-devel-202504101610-3421"
|
|
|
|
def createKubernetesPodConfig(image)
|
|
{
|
|
def podConfig = [
|
|
cloud: "kubernetes-cpu",
|
|
namespace: "sw-tensorrt",
|
|
yaml: """
|
|
apiVersion: v1
|
|
kind: Pod
|
|
spec:
|
|
qosClass: Guaranteed
|
|
nodeSelector:
|
|
nvidia.com/node_type: builder
|
|
kubernetes.io/os: linux
|
|
containers:
|
|
- name: trt-llm
|
|
image: ${image}
|
|
command: ['cat']
|
|
volumeMounts:
|
|
- name: sw-tensorrt-pvc
|
|
mountPath: "/mnt/sw-tensorrt-pvc"
|
|
readOnly: false
|
|
- name: sw-tensorrt-blossom
|
|
mountPath: "/mnt/sw-tensorrt-blossom"
|
|
readOnly: false
|
|
tty: true
|
|
resources:
|
|
requests:
|
|
cpu: 2
|
|
memory: 10Gi
|
|
ephemeral-storage: 25Gi
|
|
limits:
|
|
cpu: 2
|
|
memory: 10Gi
|
|
ephemeral-storage: 25Gi
|
|
imagePullPolicy: Always
|
|
- name: jnlp
|
|
image: urm.nvidia.com/docker/jenkins/inbound-agent:4.11-1-jdk11
|
|
args: ['\$(JENKINS_SECRET)', '\$(JENKINS_NAME)']
|
|
resources:
|
|
requests:
|
|
cpu: '2'
|
|
memory: 10Gi
|
|
ephemeral-storage: 25Gi
|
|
limits:
|
|
cpu: '2'
|
|
memory: 10Gi
|
|
ephemeral-storage: 25Gi
|
|
qosClass: Guaranteed
|
|
volumes:
|
|
- name: sw-tensorrt-pvc
|
|
persistentVolumeClaim:
|
|
claimName: sw-tensorrt-pvc
|
|
- name: sw-tensorrt-blossom
|
|
nfs:
|
|
server: 10.117.145.13
|
|
path: /vol/scratch1/scratch.svc_tensorrt_blossom
|
|
|
|
""".stripIndent(),
|
|
]
|
|
|
|
return podConfig
|
|
}
|
|
|
|
pipeline {
|
|
agent {
|
|
kubernetes createKubernetesPodConfig(DOCKER_IMAGE)
|
|
}
|
|
options {
|
|
// to better analyze the time for each step/test
|
|
timestamps()
|
|
}
|
|
parameters {
|
|
choice(name: "OPERATION", choices: ["Stats", "NormalClean", "NuclearClean", "Reset", "Config"], description: "Cache operation.")
|
|
choice(name: "BASE", choices: ["NFS", "PVC"], description: "Base directory.")
|
|
}
|
|
stages {
|
|
stage("Check or reset CCACHE") {
|
|
steps {
|
|
container("trt-llm") {
|
|
script {
|
|
// Random sleep to avoid resource contention
|
|
sleep(10 * Math.random())
|
|
|
|
switch(params.BASE) {
|
|
case "NFS":
|
|
BASE_DIR="/mnt/sw-tensorrt-blossom"
|
|
break
|
|
case "PVC":
|
|
BASE_DIR="/mnt/sw-tensorrt-pvc"
|
|
break
|
|
default:
|
|
assert false, "Unknown operation"
|
|
break
|
|
}
|
|
|
|
withEnv(["CCACHE_DIR=${BASE_DIR}/scratch.trt_ccache/llm_ccache"]) {
|
|
sh "nproc && free -g && hostname"
|
|
sh "env | sort"
|
|
sh "pwd && ls -alh"
|
|
sh "timeout 30 mount"
|
|
sh "ccache -sv"
|
|
sh "df -h"
|
|
|
|
switch(params.OPERATION) {
|
|
case "NormalClean":
|
|
sh "ccache -cz"
|
|
break
|
|
case "NuclearClean":
|
|
sh "ccache -Cz"
|
|
break
|
|
case "Reset":
|
|
sh "rm -rf ${CCACHE_DIR}"
|
|
sh "mkdir -p ${CCACHE_DIR}"
|
|
sh "printf \"max_size=300G\ntemporary_dir=/tmp/ccache\ncompression = true\n\" > ${CCACHE_DIR}/ccache.conf"
|
|
break
|
|
case "Config":
|
|
sh "printf \"max_size=300G\ntemporary_dir=/tmp/ccache\ncompression = true\n\" > ${CCACHE_DIR}/ccache.conf"
|
|
break
|
|
case "Stats":
|
|
sh "ccache -sv"
|
|
sh "cat ${CCACHE_DIR}/ccache.conf"
|
|
sh "ls -alh ${BASE_DIR}"
|
|
sh "ls -alh ${BASE_DIR}/scratch.trt_ccache"
|
|
sh "ls -alh ${BASE_DIR}/scratch.trt_ccache/llm_ccache"
|
|
break
|
|
default:
|
|
assert false, "Unknown operation"
|
|
break
|
|
}
|
|
|
|
sh "ccache -sv"
|
|
sh "df -h"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
} // stage Check or reset CCACHE
|
|
} // stages
|
|
} // pipeline
|