🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Always Be Optimal.

David Spring was arrested in Whitehall for "violent disorder", quoted as chanting "Who the f***is Allah?" and given an 18 month sentence. However, private video footage of the protest, where he can easily be identified before & after the arrest, seems to tell a different story.

People need to stop overreacting about Kamala’s plan to reduce food inflation, as if it would lead to communism, mass starvation, and the end of America. I worked in M&A in the food industry. Here’s a step-by-step summary of what would actually happen: 1. The government

CUTLASS reached 5K stars this summer with 3.5M downloads per month. Thank you for your support! github.com/NVIDIA/cutlass/

🚨 vLLM Office Hours continue on Thursday, September 5th, at 2PM ET / 11AM PT! Tyler Smith (Tyler Michael Smith), vLLM Committer & Technical Director at Neural Magic, will dive deep into using NVIDIA CUTLASS for high-performance INT8 & FP8 vLLM inference. Sign up: neuralmagic.com/community-offi…

A lot of people seem to be interested in understanding CuTe Layout algebra. Here is a progress update. Animation below demonstrates By-mode composition. Layout calculations are done by PyCute itself.

NEW: THREAD: A new ruling from Judge McBurney in Georgia overturning the abortion ban and allowing the procedure to continue has some REMARKABLE quotes. Let's take a look at just a few. 1/

BREAKING: The Nobel Prize in Physics has been awarded to ptrblock for “fundamental contributions to physics”

founder mode is realizing the government is too broken for you to go to mars so you open a work stream to fix the government

🔥 NVLink Distributed GEMMs natively in CUTLASS for all your tensor parallelism needs 🔥 blog.shi-labs.com/distributed-ge… Work done by Ali Hassani over his 2024 summer internship :)

“This is our last Hopper focused release. More exciting releases will come in 2025.” 👀👀👀👀👀👀

CUDA 12.8 just dropped with Blackwell support. TensorCore 5th Generation Family Instructions: docs.nvidia.com/cuda/parallel-…

CUTLASS 3.8 is out with full support of optimal Blackwell matrix computations and 5th generation Tensor Cores. Update your builds to use new numeric types, ample support for fused kernels, and CuTe enhancements for the Blackwell architecture. github.com/nvidia/cutlass

The open source DeepSeek-R1 model is now available as an NVIDIA NIM microservice preview on build.nvidia.com to help developers securely experiment with its advanced AI reasoning capabilities.

Congratulations, Bing Xu!

Blackwell Tensor Core 2CTA GEMM example in one slide courtesy of CuTE. github.com/NVIDIA/cutlass…