From 2dabb62984400ae4e982dc7b4f1c536079a7784d Mon Sep 17 00:00:00 2001
From: Pavithra Vijayakrishnan
<160681768+pvijayakrish@users.noreply.github.com>
Date: Thu, 25 Jul 2024 10:36:57 -0700
Subject: [PATCH] Update NGC versions post-24.07 release (#918)
---
Dockerfile | 8 ++++----
README.md | 4 ++--
docs/bls_quick_start.md | 4 ++--
docs/config.md | 2 +-
docs/ensemble_quick_start.md | 4 ++--
docs/kubernetes_deploy.md | 2 +-
docs/mm_quick_start.md | 4 ++--
docs/quick_start.md | 4 ++--
helm-chart/values.yaml | 2 +-
model_analyzer/config/input/config_defaults.py | 2 +-
10 files changed, 18 insertions(+), 18 deletions(-)
diff --git a/Dockerfile b/Dockerfile
index 856eaed53..320d93781 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -12,11 +12,11 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.06-py3
-ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.06-py3-sdk
+ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.07-py3
+ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.07-py3-sdk
-ARG MODEL_ANALYZER_VERSION=1.42.0dev
-ARG MODEL_ANALYZER_CONTAINER_VERSION=24.07dev
+ARG MODEL_ANALYZER_VERSION=1.43.0dev
+ARG MODEL_ANALYZER_CONTAINER_VERSION=24.08dev
FROM ${TRITONSDK_BASE_IMAGE} as sdk
FROM $BASE_IMAGE
diff --git a/README.md b/README.md
index d79eb630b..eb30405c9 100644
--- a/README.md
+++ b/README.md
@@ -23,8 +23,8 @@ limitations under the License.
> ##### LATEST RELEASE
>
> You are currently on the `main` branch which tracks under-development progress towards the next release.
-> The latest release of the Triton Model Analyzer is 1.41.0 and is available on branch
-> [r24.06](https://github.com/triton-inference-server/model_analyzer/tree/r24.06).
+> The latest release of the Triton Model Analyzer is 1.42.0 and is available on branch
+> [r24.07](https://github.com/triton-inference-server/model_analyzer/tree/r24.07).
Triton Model Analyzer is a CLI tool which can help you find a more optimal configuration, on a given piece of hardware, for single, multiple, ensemble, or BLS models running on a [Triton Inference Server](https://github.com/triton-inference-server/server/). Model Analyzer will also generate reports to help you better understand the trade-offs of the different configurations along with their compute and memory requirements.
diff --git a/docs/bls_quick_start.md b/docs/bls_quick_start.md
index 723215c77..997a91277 100644
--- a/docs/bls_quick_start.md
+++ b/docs/bls_quick_start.md
@@ -49,7 +49,7 @@ git pull origin main
**1. Pull the SDK container:**
```
-docker pull nvcr.io/nvidia/tritonserver:24.06-py3-sdk
+docker pull nvcr.io/nvidia/tritonserver:24.07-py3-sdk
```
**2. Run the SDK container**
@@ -59,7 +59,7 @@ docker run -it --gpus 1 \
--shm-size 2G \
-v /var/run/docker.sock:/var/run/docker.sock \
-v $(pwd)/examples/quick-start:$(pwd)/examples/quick-start \
- --net=host nvcr.io/nvidia/tritonserver:24.06-py3-sdk
+ --net=host nvcr.io/nvidia/tritonserver:24.07-py3-sdk
```
**Important:** The example above uses a single GPU. If you are running on multiple GPUs, you may need to increase the shared memory size accordingly
diff --git a/docs/config.md b/docs/config.md
index 0d31709e2..4de280275 100644
--- a/docs/config.md
+++ b/docs/config.md
@@ -153,7 +153,7 @@ cpu_only_composing_models:
[ reload_model_disable: | default: false]
# Triton Docker image tag used when launching using Docker mode
-[ triton_docker_image: | default: nvcr.io/nvidia/tritonserver:24.06-py3 ]
+[ triton_docker_image: | default: nvcr.io/nvidia/tritonserver:24.07-py3 ]
# Triton Server HTTP endpoint url used by Model Analyzer client"
[ triton_http_endpoint: | default: localhost:8000 ]
diff --git a/docs/ensemble_quick_start.md b/docs/ensemble_quick_start.md
index 45c1cbade..d9bd9d33c 100644
--- a/docs/ensemble_quick_start.md
+++ b/docs/ensemble_quick_start.md
@@ -55,7 +55,7 @@ mkdir examples/quick-start/ensemble_add_sub/1
**1. Pull the SDK container:**
```
-docker pull nvcr.io/nvidia/tritonserver:24.06-py3-sdk
+docker pull nvcr.io/nvidia/tritonserver:24.07-py3-sdk
```
**2. Run the SDK container**
@@ -65,7 +65,7 @@ docker run -it --gpus 1 \
--shm-size 1G \
-v /var/run/docker.sock:/var/run/docker.sock \
-v $(pwd)/examples/quick-start:$(pwd)/examples/quick-start \
- --net=host nvcr.io/nvidia/tritonserver:24.06-py3-sdk
+ --net=host nvcr.io/nvidia/tritonserver:24.07-py3-sdk
```
**Important:** The example above uses a single GPU. If you are running on multiple GPUs, you may need to increase the shared memory size accordingly
diff --git a/docs/kubernetes_deploy.md b/docs/kubernetes_deploy.md
index c2d962969..2497cab3b 100644
--- a/docs/kubernetes_deploy.md
+++ b/docs/kubernetes_deploy.md
@@ -79,7 +79,7 @@ images:
triton:
image: nvcr.io/nvidia/tritonserver
- tag: 24.06-py3
+ tag: 24.07-py3
```
The model analyzer executable uses the config file defined in `helm-chart/templates/config-map.yaml`. This config can be modified to supply arguments to model analyzer. Only the content under the `config.yaml` section of the file should be modified.
diff --git a/docs/mm_quick_start.md b/docs/mm_quick_start.md
index 6ed20969f..7ace3b5e9 100644
--- a/docs/mm_quick_start.md
+++ b/docs/mm_quick_start.md
@@ -49,7 +49,7 @@ git pull origin main
**1. Pull the SDK container:**
```
-docker pull nvcr.io/nvidia/tritonserver:24.06-py3-sdk
+docker pull nvcr.io/nvidia/tritonserver:24.07-py3-sdk
```
**2. Run the SDK container**
@@ -58,7 +58,7 @@ docker pull nvcr.io/nvidia/tritonserver:24.06-py3-sdk
docker run -it --gpus all \
-v /var/run/docker.sock:/var/run/docker.sock \
-v $(pwd)/examples/quick-start:$(pwd)/examples/quick-start \
- --net=host nvcr.io/nvidia/tritonserver:24.06-py3-sdk
+ --net=host nvcr.io/nvidia/tritonserver:24.07-py3-sdk
```
## `Step 3:` Profile both models concurrently
diff --git a/docs/quick_start.md b/docs/quick_start.md
index 431cebc31..0769c4840 100644
--- a/docs/quick_start.md
+++ b/docs/quick_start.md
@@ -49,7 +49,7 @@ git pull origin main
**1. Pull the SDK container:**
```
-docker pull nvcr.io/nvidia/tritonserver:24.06-py3-sdk
+docker pull nvcr.io/nvidia/tritonserver:24.07-py3-sdk
```
**2. Run the SDK container**
@@ -58,7 +58,7 @@ docker pull nvcr.io/nvidia/tritonserver:24.06-py3-sdk
docker run -it --gpus all \
-v /var/run/docker.sock:/var/run/docker.sock \
-v $(pwd)/examples/quick-start:$(pwd)/examples/quick-start \
- --net=host nvcr.io/nvidia/tritonserver:24.06-py3-sdk
+ --net=host nvcr.io/nvidia/tritonserver:24.07-py3-sdk
```
## `Step 3:` Profile the `add_sub` model
diff --git a/helm-chart/values.yaml b/helm-chart/values.yaml
index df2f550ee..6de3bfef8 100644
--- a/helm-chart/values.yaml
+++ b/helm-chart/values.yaml
@@ -41,4 +41,4 @@ images:
triton:
image: nvcr.io/nvidia/tritonserver
- tag: 24.06-py3
+ tag: 24.07-py3
diff --git a/model_analyzer/config/input/config_defaults.py b/model_analyzer/config/input/config_defaults.py
index 13d6df047..8afa19c47 100755
--- a/model_analyzer/config/input/config_defaults.py
+++ b/model_analyzer/config/input/config_defaults.py
@@ -63,7 +63,7 @@
DEFAULT_REQUEST_RATE_SEARCH_ENABLE = False
DEFAULT_CONCURRENCY_SWEEP_DISABLE = False
DEFAULT_TRITON_LAUNCH_MODE = "local"
-DEFAULT_TRITON_DOCKER_IMAGE = "nvcr.io/nvidia/tritonserver:24.06-py3"
+DEFAULT_TRITON_DOCKER_IMAGE = "nvcr.io/nvidia/tritonserver:24.07-py3"
DEFAULT_TRITON_HTTP_ENDPOINT = "localhost:8000"
DEFAULT_TRITON_GRPC_ENDPOINT = "localhost:8001"
DEFAULT_TRITON_METRICS_URL = "http://localhost:8002/metrics"