Look what just arrived for our dev team in the labs … Reservations for NVIDIA DGX Spark — your own desktop AI supercomputer — close in less than a week. Get ready to #SparkSomethingBig https://
nvidia.com/en-us/products
/workstations/dgx-spark/
…
COMPUTING
-
NVIDIA DGX Spark Desktop AI Supercomputer Reservations Open
By
–
-
K2 Think: Open-Source Reasoning Model 20x Faster on Cerebras
By
–
K2 Think is now available and runs fastest on Cerebras Inference at 2,000 TPS on Cerebras – 20x faster than GPU.
— Cerebras (@cerebras) 10 septembre 2025
Launched by @mbzuai and @G42ai, K2 Think is a world leading open-source reasoning model that beats GPT OSS 120B and DeepSeek on math and reasoning. pic.twitter.com/fsRl5QhlaXK2 Think is now available and runs fastest on Cerebras Inference at 2,000 TPS on Cerebras – 20x faster than GPU. Launched by @mbzuai and @G42ai
, K2 Think is a world leading open-source reasoning model that beats GPT OSS 120B and DeepSeek on math and reasoning. -
Tool Call Outputs as Container Files: Data Processing Possibilities
By
–
Can tool call outputs directly become files in the container? I’d really want that – open up a ton of data processing possibilities.
-
NCCL Timeout Issue with Qwen3 LLM Engine Initialization
By
–
`accelerate test` works with the default config… But the script above hangs for 10 minutes likely due to the NCCL timeout. Somewhere between these two log lines: INFO [core(.)py:74] Initializing a V1 LLM engine (v0.10.1.1) with config: model='unsloth/Qwen3-4B-Base'
INFO -
Training Qwen3 Multi-GPU Setup with Accelerate Library
By
–
Anyone manage to get Qwen3 to train on multiple GPUs using `accelerate`? With a fresh install, I can't get even SFT to work with two 3090s.@UnslothAI The demo notebooks are nice, but a reproducible script known to work would be great, ideally with version dependencies pinned! https://t.co/8FkFpC3pdO
— Alex J. Champandard 🌱 (@alexjc) 10 septembre 2025Anyone manage to get Qwen3 to train on multiple GPUs using `accelerate`? With a fresh install, I can't get even SFT to work with two 3090s. @UnslothAI The demo notebooks are nice, but a reproducible script known to work would be great, ideally with version dependencies pinned!
-
FFmpeg container installation and available binaries documentation
By
–
Also could you install ffmpeg into the container? And provide a documented list somewhere of all of the available binaries – I just had to create one myself https://
claude.ai/share/c9bd85ba
-71d2-4c4b-a49d-07924b657f61
… -
Claude Web App Now Executes Python Code Scripts
By
–
Yes definitely – it only works in the web app right now and you have to turn on the feature in settings (if it's available to your account) Here's an example where I pasted in Python code and told it to "Run this python script and show me the result" https://
claude.ai/share/4d9c603e
-c88d-4b94-bf8b-7b8e24444434
… -
Nvidia Pro Mode: Open Source Nemotron 9B Chaining
By
–
Introducing: Nvidia Pro Mode!
— Matt Shumer (@mattshumer_) 10 septembre 2025
Basically GPT-5 Pro, but for the new Nvidia open source model 🙂
Pro Mode chains together up to 50 instances of the new Nemotron 9B model, enabling it to produce a better answer than one instance alone could create!
Open source, link here: pic.twitter.com/cMDzTZp9bXIntroducing: Nvidia Pro Mode! Basically GPT-5 Pro, but for the new Nvidia open source model 🙂 Pro Mode chains together up to 50 instances of the new Nemotron 9B model, enabling it to produce a better answer than one instance alone could create! Open source, link here:
-
Charles forking processes powerful hardware computing infrastructure
By
–
Dammit Charles. You and your forking processes on beefy hardware. Now you're making us all gay.
-
Algorithm Reputation Impact: Block Effects on Social Rankings
By
–
FAQ #3 i'm blocked by like 50k people, is that bad? > you've been algorithmically buried blocks are a direct nerf to your reputation graph, too many and your simcluster ranking crumbles