October 4, 2024

CLI update announcement

We have updated our CLI commands to enhance functionality and improve user experience. As part of the recent updates, including the renaming of VESSL Serve to VESSL Service and the Pipeline GA, the following changes have been made to the VESSL CLI:

Deprecated Commands

  1. vessl serve update

  2. vessl serve revision list, vessl serve revision show, vessl serve revision terminate

  3. vessl serve gateway show

New Commands

  • vessl service create
  • vessl service list
  • vessl service read
  • vessl service terminate
  • vessl service scale
  • vessl service split-traffic
  • vessl service create-yaml

Notes

  • If you have scripts or workflows using the deprecated commands, please update them to use the new commands.
  • For more information on each command, use the --help option. For example: vessl service create --help

August 31, 2024

Pricing plan section updated in VESSL documentation

We’ve created the pricing plan section in the Resources section. Also, our pricing plan (GCP, AWS) details have been updated in the VESSL documentation. Users now have more clarity on compute options and corresponding costs. Pro users continue to receive 100 credits every month, with each credit equivalent to $1.00. For more details, refer to the updated Pricing & Compute section in the documentation.


August 5, 2024

Pipeline general availability (GA) update

VESSL Pipeline has reached general availability, designed to enhance the execution of complex ML workflows such as LLM fine-tuning, data preprocessing, and batch inference.

  • Key features:
    • Drag-and-drop GUI: Intuitive interface for modifying and visualizing pipeline flows.
    • Infra-as-code: YAML-based code interface integration, enabling effective version management of pipeline modifications.
    • High visibility and debuggability: Improved debugging capabilities with natural separation of task stages, including endpoint access and re-execution for failed tasks.
    • Human-in-the-loop: Built-in support for scenarios requiring user intervention, such as intermediate result feedback and decision-making based on input/output.

Three early adopters have successfully integrated their services into the running pipeline. If you’re interested in integrating the VESSL Pipeline, please contact our sales team.

Learn more about Pipeline

With the Pipeline section, you can explore it in detail.


July 12, 2024

Website V2 Update

We are excited to announce the launch of VESSL 2.0, introducing a sleek, user-centric interface designed to streamline the MLOps experience.

  • New features:
    • Self-service user interface: Seamless transition from model exploration to deployment, with tools like VESSL Hub for testing and fine-tuning open-source models, and VESSL Service for creating scalable APIs.
    • Service revision creation through web console: Previously only available through CLI, users can now create service revisions in both Provisioned and Serverless Mode through the UI.
    • CMD+K navigation: Quick access to any entity within VESSL, enhancing productivity and efficiency.

With VESSL 2.O, you can enjoy the sleek new interface, intuitive web console and also powerful CMD+K navigation. Visit our website now.

VESSL offers a unified interface across multiple cloud providers and on-premise servers, facilitating large-scale machine learning deployments.


May 12, 2024

Serverless deployment

Our serverless deployment infrastructure is the easiest way to scale inference workloads on remote GPUs. With continuous batching, effortless autoscaling, fast cold start, full observability, and more, your APIs are production-ready for full-spectrum AI & LLM applications.

  • Key features:
    • Cost efficiency: Serverless Mode operates on a scale-to-zero basis, ensuring that users only pay for the resources they actually use.
    • Automatic scaling: Real-time scaling based on workload demands without the need for complex configurations.
    • Simplified deployment: Minimal configuration required, making deployment accessible to all users.
    • High availability and resilience: Fast startup times (average 17 seconds) and robust infrastructure ensure high availability with minimal cold starts.

Refer to our docs to put custom Llama 3 in action Text Generation Inference (TGI), in 3 simple steps.

  1. Create a remote GPU-accelerated container
  2. Create an endpoint with Llama 3 from Hugging Face
  3. Send an HTTPS request to the deployed service

April 12, 2024

Announcing VESSL Serve

VESSL Service is the easiest way to Deploy custom models & generative AI applications and scale inference with ease. Deploy any models, to any clouds, at any scale in minutes without wasting hours on API servers, load balancing, automatic scaling, and more Read our release post or try our the Llama 3 example to learn more.


March 11, 2024

Cloud storage support for VESSL Run

Import your data from and export results to a cloud storage like AWS S3 and GCP GCS for your run. You can also bring your own cloud storage by adding the credential of your cloud storage on our improved Secrets page. Refer to our docs for a step-by-step guide.

Google Cloud Storage FUSE

We are brining FUSE support for GCS. FUSE helps you work with object storage through familiar filesystem operations without needing to directly use the proprietary GCS SDKs.


January 31, 2024

New get started guide

We’ve updated our documenation with a new get started guide. The new guide covers everything from product overview to the latest use cases of our product in Gen AI & LLM.

Follow along our new guide here.

New & Improved

  • Added a new managed cloud option built on Google Cloud
  • Renamed our default managed Docker images to torch:2.1.0-cuda12.2-r3

December 28, 2023

Announcing VESSL Hub

VESSL Hub is a collection of one-click recipes for the latest open-source models like Llama2, Mistral 7B, and StableDiffusion. Built on our fullstack AI infrastructure, Hub provides the easiest way to explore and deploy models.

Fine-tune and deploy the latest models on our production-grade fullstack cloud infrastructure with just a single click. Read about the release on our blog or try it out now at vessl.ai/hub.