dstack

1.2K posts

dstack

dstack

@dstackai

Control plane for agents & engineers to provision compute and run training & inference across NVIDIA, AMD, and other chips — on clouds, Kubernetes, and on-prem.

github.com/dstackai/dstack Katılım Ocak 2020
56 Takip Edilen1.5K Takipçiler
Sabitlenmiş Tweet
dstack
dstack@dstackai·
Infrastructure orchestration is becoming an agent skill. When agents run experiments, training, and eval autonomously, they now can provision compute, schedule workloads, and track state, all inside the loop. New post on what this means for platform teams, providers, and the orchestration layer dstack.ai/blog/agentic-o…
English
6
12
115
402.6K
dstack retweetledi
Vikram
Vikram@msharmavikram·
@dstackai now comes with @nvidia Dynamo. 🚀🚀🚀 Now you can provision compute and run training, inference, and sandboxes in one go across inference engines and get sol performance 🔥
dstack@dstackai

dstack 0.20.20 is out 🚀 New in services: Prefill-Decode disaggregated inference with @NVIDIA Dynamo, with workers running @lmsysorg SGLang, @vllm_project, or TensorRT-LLM. Also: ⚡️ Easier provisioning and management of @awscloud clusters that use EFA ⚡️ Sharing gateways across projects github.com/dstackai/dstac…

English
0
2
11
738
dstack retweetledi
Anish
Anish@athreesh·
dstack team stays cooking! Being able to deploy Dynamo in any environment is super valuable and dstack gets rid of any friction🫡🤝
dstack@dstackai

dstack 0.20.20 is out 🚀 New in services: Prefill-Decode disaggregated inference with @NVIDIA Dynamo, with workers running @lmsysorg SGLang, @vllm_project, or TensorRT-LLM. Also: ⚡️ Easier provisioning and management of @awscloud clusters that use EFA ⚡️ Sharing gateways across projects github.com/dstackai/dstac…

English
1
3
5
600
dstack
dstack@dstackai·
dstack 0.20.20 is out 🚀 New in services: Prefill-Decode disaggregated inference with @NVIDIA Dynamo, with workers running @lmsysorg SGLang, @vllm_project, or TensorRT-LLM. Also: ⚡️ Easier provisioning and management of @awscloud clusters that use EFA ⚡️ Sharing gateways across projects github.com/dstackai/dstac…
English
3
2
10
1.7K
dstack
dstack@dstackai·
The agentic engineering wave is coming to AI infra, but Kubernetes is too messy to keep up, and is a real bottleneck. The founder of dstack, @andrey_cheptsov, sat down with @readsail at @nvidia GTC to talk about GPU orchestration. Big thanks to @makora_ai and @SemiAnalysis_ for organizing the interview!
English
1
2
5
255
dstack
dstack@dstackai·
We wrote up a guide for both devs and AI agents on how to use the dstack CLI and API to manage GPU and CPU workloads. No more using raw Kubernetes or cloud-proprietary interfaces. Go for an open, cloud-agnostic way to manage AI infrastructure. dstack.ai/docs/guides/cl…
English
1
2
4
253
dstack retweetledi
dstack
dstack@dstackai·
dstack now supports deploying @lmsysorg SGLang with Prefill-Decode disaggregation via @lightseekorg's Shepherd Model Gateway. One service config, three replica groups: router, prefill, and decode workers scale independently across any GPU cloud or on-prem cluster. dstack.ai/blog/smg
English
2
8
14
341.8K
dstack
dstack@dstackai·
We had our AI Infra meetup in San Francisco last week, co-hosted with @CrusoeAI and @lmsysorg. We've put the slides from each talk below so you can go through the material at your own pace. 👇 🧵 1/10
dstack tweet media
English
1
6
9
2.5K
dstack
dstack@dstackai·
If you’re interested in an open-source orchestration platform that simplifies training and inference across GPU vendors, clouds, and open-source software stacks, check out our GitHub repo: github.com/dstackai/dstac… 🧵 10/10
English
0
1
3
127
dstack
dstack@dstackai·
We thank everyone who joined the meetup and especially our co-hosts @CrusoeAI and @lmsysorg. We're already working on the next AI Infra Meetup. See you at the next one! 🧵 9/10
dstack tweet media
English
1
1
5
120

Keşfet

@nvidia @lmsysorg @vllm_project @awscloud @NVIDIA @andrey_cheptsov @readsail @makora_ai