From 7bb3f0db9a335bff39a9df2ff1bafa0c1c32ba11 Mon Sep 17 00:00:00 2001 From: David Chu Date: Wed, 18 Feb 2026 17:02:15 -0800 Subject: [PATCH 1/3] Some documentation fixes + new articles on logs and worker states --- docs.json | 7 +++ documentation/serverless/SDKoverview.mdx | 4 +- documentation/serverless/architecture.mdx | 4 +- documentation/serverless/logging.mdx | 51 ++++++++++++++++ documentation/serverless/quickstart.mdx | 2 +- documentation/serverless/worker-states.mdx | 64 +++++++++++++++++++++ images/endpoint-log.webp | Bin 0 -> 147376 bytes images/serverless-architecture.webp | Bin 51738 -> 57140 bytes images/worker-log.webp | Bin 0 -> 44378 bytes 9 files changed, 127 insertions(+), 5 deletions(-) create mode 100644 documentation/serverless/logging.mdx create mode 100644 documentation/serverless/worker-states.mdx create mode 100644 images/endpoint-log.webp create mode 100644 images/worker-log.webp diff --git a/docs.json b/docs.json index 5deb71c..9507528 100644 --- a/docs.json +++ b/docs.json @@ -104,6 +104,13 @@ }, "documentation/serverless/workergroup-parameters", "documentation/serverless/creating-new-pyworkers", + { + "group": "Monitoring and Debug", + "pages": [ + "documentation/serverless/worker-states", + "documentation/serverless/logging" + ] + }, "documentation/serverless/pricing", { "group": "Pre-built Templates", diff --git a/documentation/serverless/SDKoverview.mdx b/documentation/serverless/SDKoverview.mdx index 3a2ab5e..b271f8f 100644 --- a/documentation/serverless/SDKoverview.mdx +++ b/documentation/serverless/SDKoverview.mdx @@ -34,6 +34,6 @@ The SDK manages the following core functions for the client: ## Why Use the SDK -While there are other ways to interact with serverless endpoint—such as the CLI and the REST API—the SDK is the **most powerful and easiest** method to use. It is the recommended approach for most applications due to its higher-level abstractions, reliability, and ease of integration into Python-based workflows. +While there are other ways to interact with serverless endpoint — such as the CLI and the REST API — the SDK is the **most powerful and easiest** method to use as it incorporates all best practices for using the API. It is the **recommended approach** for most applications due to its higher-level abstractions, reliability, and ease of integration into Python-based workflows. -If the Python SDK is not usable for your application, please contact support to request further assistance. We're happy to help. \ No newline at end of file +If the Python SDK or CLI are usable for your application, please contact support to request further assistance. We're happy to help. \ No newline at end of file diff --git a/documentation/serverless/architecture.mdx b/documentation/serverless/architecture.mdx index ff6b5e6..2879f62 100644 --- a/documentation/serverless/architecture.mdx +++ b/documentation/serverless/architecture.mdx @@ -34,7 +34,7 @@ An **Endpoint** is the highest-level construct in Vast Serverless. Endpoints are An endpoint consists of: - A named endpoint identifier -- One or more Workergroups +- Typically one workergroup - Endpoint parameters such as `max_workers`, `min_load`, `min_workers`, `cold_mult`, `min_cold_load`, and `target_util` Users typically create one endpoint per **use case** (for example, text generation or image generation) and per **environment** (production, staging, development). Each endpoint acts as a router and load balances requests across its pool of managed workers based on worker queue time. @@ -51,7 +51,7 @@ Each Workergroup includes: - Hardware requirements such as `gpu_ram` - A set of GPU instances (workers) created from the template -Multiple Workergroups can exist within a single Endpoint, each with different configurations. This enables advanced use cases such as hardware comparison, gradual model rollout, or mixed-model serving. For many applications, a single Workergroup is sufficient. +Multiple Workergroups can exist within a single Endpoint, each with different configurations. For most users, a single Workergroup is sufficient and recommended, advanced use cases such as mixed-model serving and hardware comparisons can be enabled with multiple Workergorups. For such use cases, please contact Vast for assistance and best practices. ### Workers diff --git a/documentation/serverless/logging.mdx b/documentation/serverless/logging.mdx new file mode 100644 index 0000000..030aef1 --- /dev/null +++ b/documentation/serverless/logging.mdx @@ -0,0 +1,51 @@ +--- +title: Endpoint and Worker Logs +description: Learn how to access Vast serverless logs +"canonical": "/documentation/serverless/logging" +--- + +