corpus.blog
43,659 blogs · 5,563,491 posts Claim your blog
Record · corpus.blog/posts/01a07d5d-88d1-7203-af2c-4b784873561f

Modular: CUDA is the incumbent, but is it any good? (Democratizing AI Compute, Part 4)

Modular · published 20 February 2025

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at modular.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
External links
24
Words captured
1,725

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://www.llamaindex.ai/
llamaindex.ai
https://www.langchain.com/
langchain.com
https://github.com/microsoft/autogen?tab=readme-ov-file
github.com
https://x.com/ordax/status/1876624589993976295
x.com
https://github.com/vllm-project/vllm/issues/129?utm_source=chatgpt.com
github.com
https://dev.to/moseo/solving-the-version-conflicts-between-the-nvidia-driver-and-cuda-toolkit-2n2?utm_source=chatgpt.com
dev.to
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision Read at the source ↗
pytorch.org
https://github.com/Dao-AILab/flash-attention/blob/a09abcd32d3cae4d83b313446e887f38d02b799f/hopper/copy_sm90_bulk_reduce.hpp
github.com
https://leimao.github.io/blog/NVIDIA-Tensor-Core-Programming/
leimao.github.io
https://www.tomshardware.com/tech-industry/artificial-intelligence/deepseeks-ai-breakthrough-bypasses-industry-standard-cuda-uses-assembly-like-ptx-programming-instead
tomshardware.com
https://developer.nvidia.com/blog/programming-tensor-cores-cuda-9/
developer.nvidia.com
https://docs.nvidia.com/cuda/cuda-c-programming-guide/
docs.nvidia.com
https://github.com/NVIDIA/cutlass
github.com
https://developer.nvidia.com/blog/reducing-application-build-times-using-cuda-c-compilation-aids/
developer.nvidia.com
https://xkcd.com/303/
xkcd.com
https://www.visualcapitalist.com/the-supercomputer-in-your-pocket/
visualcapitalist.com
https://www.datacenterdynamics.com/en/news/nvidia-gpu-shipments-totaled-376m-in-2023-equating-to-a-98-market-share-report/
datacenterdynamics.com
https://en.wikipedia.org/wiki/Jim_Keller_(engineer
en.wikipedia.org
https://www.tomshardware.com/tech-industry/artificial-intelligence/jim-keller-criticizes-nvidias-cuda-and-x86-cudas-a-swamp-not-a-moat-x86-was-a-swamp-too
tomshardware.com
https://www.wsj.com/tech/ai/ai-nvidia-apple-amd-jensen-huang-software-bb581f5a
wsj.com
https://www.forbes.com/sites/karlfreund/2023/09/08/nvidia-adds-new-software-that-can-double-h100-inference-performance/
forbes.com
https://docs.nvidia.com/cuda/blackwell-compatibility-guide/
docs.nvidia.com
https://docs.nvidia.com/cuda/parallel-thread-execution/
docs.nvidia.com
https://www.washingtonpost.com/business/2024/11/05/nvidia-tops-apple/
washingtonpost.com
Elsewhere on modular.com (2)