We got @DeepSeek-V4.1-Flash running in EXL3 on 4× Sparks!
This is a dev post classified by Jev as Hosting & infra (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
We got @DeepSeek-V4.1-Flash running in EXL3 on 4× Sparks! I was happy to colab with Cruz (@ViC305) and get his vllm-exl3 and his DeepSeek-V4.1 recipe working on TP=4! Single-stream decode: 30.2 tok/s prose, 33.4 tok/s on code, with a best warm 33.37 tok/s Aggregate: 27.8 / 43.9 / 57.7 / 61.5 tok/s at c=1/2/4/8. As you can see, there is opportunity for growth here, but it is going to take a week or so of addressing some drafter issues that might not get me much, so I am switching gears to another project for now, but might come back to this later. KV budget: 3.97m tokens Context: full 1m
Posted by Chris Fontes (201 followers) 1 h ago · 5 likes · 15.5k views · view the original post on X. Kept by the Dev Radar as Hosting & infra. Tools mentioned: deepseek-v4.1-flash-exl3-dgx-spark-recipe.
More dev work like this
- #RHEL is now supported by Robot Operating System (ROS2) as a tier-1 platform, bringing… — @RedHat
- Agent Runners picks these up along with AI Gateway, so an agent building in Netlify can… — @Netlify
- Spent a bit of time tuning NCCL for TP=4 GLM 5.3 Flash on 4x DGX Sparks. Bumped to… — @mmastrac
- Introducing the prerelease of Amazon Bedrock AgentCore runtime as a compute provider for… — @temporalio
- every open RL framework handwaves the sandbox layer like it's someone else's problem. — @arjunkocher
- #CloudflareConnect 2026 is bringing together the engineers, architects, and leaders… — @Cloudflare
- Cloud APIs don’t need a custom SDK for every query. — @DanKornas
- Google just open-sourced a Kubernetes-like orchestrator for running AI agents. — @twtayaan
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 22.6k posts from 5k X accounts over the last 21 days, 2.6k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 15:21 UTC. Full method.