curius graph

all pages

showing 110001-110050 of 203683 pages (sorted by popularity)
lecture12
lecture13
Adjusting for GPU Memory Bandwidth Tradeoffs | Apple Developer Documentation
Metal Performance Shaders | Apple Developer Documentation
Fast transformer inference with Metal Performance Shaders · Explosion
[2212.09720] The case for 4-bit precision: k-bit Inference Scaling Laws
Efficient Systems for Foundation Models
ggml.ai
Add GPU support to ggml · ggerganov/llama.cpp · Discussion #915
Tianqi Chen
https://web.stanford.edu/~learnest/sail/
Go To Statement Considered Harmful: A Retrospective
lecture14
TPUs vs GPUs for Transformers (BERT) — Tim Dettmers
How To Build and Use a Multi GPU System for Deep Learning — Tim Dettmers
How to Parallelize Deep Learning on GPUs Part 1/2: Data Parallelism — Tim Dettmers
One weird trick for parallelizing convolutional neural networks | PDF
Google Code Archive - Long-term storage for Google Code Project Hosting.
Stanford Artificial Intelligence Lab, SAIL-1969-1974, photos
Addendum Paper for the International Forum of University Science Park, China (2004)
sail-films-index
Early Computers at Stanford - Stanford CSD History
SAIL-1976
WebGPT/other/int8-gemm.js at main · 0hq/WebGPT · GitHub
Notion – The all-in-one workspace for your notes, tasks, wikis, and databases.
Introduction - Learn WebGPU for C++ documentation
First Color - Learn WebGPU for C++ documentation
Hello Triangle - Learn WebGPU for C++ documentation
Design and Architecture — tvm 0.15.dev0 documentation
cs140e-24win/notes/devices/DEVICES.md at main · dddrrreee/cs140e-24win
Make (software) - Wikipedia
Practical Makefiles, by example
proceedings.neurips.cc/paper/2018/file/fd9dd764a6f1d73f4340d570804eacc4-Paper.pdf
Voyager: An Open-Ended Embodied Agent with Large Language Models | Abstract
Jargon File - Wikipedia
PT2 Manifesto - Google Docs
PT2 Architecture - Google Docs
Memory-Limited Layers User's Guide - NVIDIA Docs
cs140e-24win/labs/13-ss-equiv/README.md at main · dddrrreee/cs140e-24win
Anna Ivanova
Claire Baum | LinkedIn
Genie: Generative Interactive Environments - Google DeepMind
the world’s largest distributed LLM training job on TPU v5e | Google Cloud Blog
Reverse-Engineering cuBLAS
wangzyon/NVIDIA_SGEMM_PRACTICE: Step-by-step optimization of CUDA SGEMM
How to use distributed shared memory in CUDA for inter-thread-block communication
Outperforming cuBLAS on H100: a Worklog
CHM Releases AlexNet Source Code - CHM
👨🏾‍🎓 my journey from underachieving student to moderately competent adult [2016] - @visakanv's blog
The future of urban housing is energy efficient refrigerators | MIT Technology Review