Skip to content
Live
Trending storyDeveloping

GitHub Copilot v0.33.0 released

5 reports2 outlets21 hours agoUpdate

The story so far

AI overview

GitHub Copilot released version 0.33.0, adding 927 commits and new models and features supported by 389 contributors, including the 501B MoE Reflection Beam-1.0 and its DFlash2 renderer. This version upgrades to PyTorch 2.14 and only supports CUDA 13.0, while introducing AWS EFA image support for multi-node deployment.

AI-written from the reports · Updated 18 hours ago

Latest14 Nov, 05:12
vLLM v0.34.0rc3 release

Developments

4 developments

  1. 14 Nov, 05:12 · 1 reports
    v0.34.0rc3 release
    vLLM releases：vLLM v0.34.0rc3 release
  2. 9 Nov, 02:38 · 1 reports
    v0.34.0rc0 release
    vLLM releases：vLLM v0.34.0rc0 released: migrating Gemma and StableLM to the Transformers backend
  3. 6 Nov, 08:00 · 1 reports
    Migrating vLLM to the LibTorch Stable ABI
    vLLM Blog：vLLM migrates to LibTorch Stable ABI
  4. 31 Oct, 15:15 · 2 reports
    v0.33.0
    vLLM releases：vLLM v0.33.0 released: adding 927 commits, 389 contributors and 10 new models, supporting PyTorch 2.14 and CUDA 13.0

Coverage timeline

Follow the coverage to see every side of the story.

14 Nov
  1. vLLM releases
    vLLM v0.34.0rc3 release

    vLLM v0.34.0rc3 release, supports 8k context, speed increased 3.5x, open source.

9 Nov
  1. vLLM releases
    vLLM v0.34.0rc0 released: migrating Gemma and StableLM to the Transformers backend

    vLLM v0.34.0rc0 released, migrating Gemma and StableLM to the Transformers backend.

6 Nov
  1. vLLM Blog
    vLLM migrates to LibTorch Stable ABI

    vLLM releases LibTorch ABI Stable CUDA since v0.33.0, allowing PyTorch upgrade without rebuilding.

1 Nov
  1. vLLM releases
    vLLM v0.33.0 released: new model and features with 927 commits and support from 389 contributors.

    vLLM v0.33.0 released, including 927 commits and support from 389 contributors, new 501B MoE Reflection Beam-1.0 and its DFlash2 renderer.

31 Oct
  1. vLLM releases
    vLLM v0.33.0 released: adding 927 commits, 389 contributors and 10 new models, supporting PyTorch 2.14 and CUDA 13.0

    vLLM v0.33.0 released, adding 927 commits, 389 contributors, introducing 10 new models such as Reflection Beam-1.0 (501B MoE, 23B active) and Yandex AliceAI-Foundation-80B-A3B

Heat over time

Now
6
Peak
914 Nov, 08:00
24h change
–

Hover or tap the chart to see each hour; use the arrow keys on a keyboard.