mirror of
https://github.com/osmarks/website
synced 2026-03-02 22:39:45 +00:00
new Graphcore post
This commit is contained in:
osmarks
448
links_cache.json
448
links_cache.json
@@ -4794,5 +4794,453 @@
|
||||
"date": "2025-07-11T01:01:26.883Z",
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://en.wikipedia.org/wiki/Denver": {
|
||||
"excerpt": "This article is about the city and county in Colorado. For other uses, see Denver (disambiguation).",
|
||||
"title": "Denver",
|
||||
"author": "Contributors to Wikimedia projects",
|
||||
"date": "2001-09-26T14:34:32Z",
|
||||
"website": "Wikimedia Foundation, Inc.",
|
||||
"auto": true
|
||||
},
|
||||
"https://en.wikipedia.org/wiki/Mexico_City": {
|
||||
"excerpt": "Mexico City",
|
||||
"title": "Mexico City",
|
||||
"author": "Contributors to Wikimedia projects",
|
||||
"date": "2001-10-30T04:58:27Z",
|
||||
"website": "Wikimedia Foundation, Inc.",
|
||||
"auto": true
|
||||
},
|
||||
"https://worksinprogress.co/issue/the-magic-of-through-running/": {
|
||||
"excerpt": "Commuter trains often stop at the edge of cities. Building a short tunnel to join them up is often by far the most efficient way to improve a city's transport.",
|
||||
"title": "The magic of through running",
|
||||
"author": "wip-admin",
|
||||
"date": "2025-06-12T08:15:50+00:00",
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://www.businessinsider.com/the-8-fastest-elevators-in-the-world-2013-1": {
|
||||
"excerpt": "Check out the eight fastest elevators worldwide, showcasing engineering marvels that redefine vertical transportation.",
|
||||
"title": "Asian Skyscrapers Dominate A New List Of The World's Fastest Elevators",
|
||||
"author": "Megan Willett-Wei",
|
||||
"date": "2013-01-23T17:07:46Z",
|
||||
"website": "Business Insider",
|
||||
"auto": true
|
||||
},
|
||||
"https://westhunt.wordpress.com/2012/03/23/a-sobering-thought/": {
|
||||
"excerpt": "In scuba diving, pressure increases by one atmosphere with each ten meters of depth. As pressure increases, people breathing standard air mix gradually get silly. This is mainly caused by the in…",
|
||||
"title": "A sobering thought",
|
||||
"author": "Posted on",
|
||||
"date": "2012-03-23T19:19:23+00:00",
|
||||
"website": "West Hunter",
|
||||
"auto": true
|
||||
},
|
||||
"https://pubmed.ncbi.nlm.nih.gov/1130736/": {
|
||||
"excerpt": "Nitrogen has recognized narcotic potential at hyperbaric pressures. No narcotic effect of helium has been demonstrated at any pressure. We evaluated the effect of nitrogen in air at one atmosphere on human performance by comparing it with helium-oxygen using a four-alternative divided-attention task …",
|
||||
"title": "The anesthetic effect of air at atmospheric pressure - PubMed",
|
||||
"author": "P M Winter, D L Bruce, M J Bach, G W Jay, E I Eger 2nd",
|
||||
"date": null,
|
||||
"website": "PubMed",
|
||||
"auto": true
|
||||
},
|
||||
"https://web.archive.org/web/20080914174633/http://www.techdiver.ws/exotic_gases.shtml": {
|
||||
"excerpt": "Exotic diving gases",
|
||||
"title": "Exotic diving gases",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://en.wikipedia.org/wiki/Oxygen_toxicity": {
|
||||
"excerpt": "Oxygen toxicity is a condition resulting from the harmful effects of breathing molecular oxygen (O2) at increased partial pressures. Severe cases can result in cell damage and death, with effects most often seen in the central nervous system, lungs, and eyes. Historically, the central nervous system condition was called the Paul Bert effect, and the pulmonary condition the Lorrain Smith effect, after the researchers who pioneered the discoveries and descriptions in the late 19th century. Oxygen toxicity is a concern for underwater divers, those on high concentrations of supplemental oxygen, and those undergoing hyperbaric oxygen therapy.",
|
||||
"title": "Oxygen toxicity",
|
||||
"author": "Contributors to Wikimedia projects",
|
||||
"date": "2004-02-09T20:09:06Z",
|
||||
"website": "Wikimedia Foundation, Inc.",
|
||||
"auto": true
|
||||
},
|
||||
"https://www.ifixit.com/News/11986/iphones-are-allergic-to-helium": {
|
||||
"excerpt": "This is the kind of tale that you don’t hear every day. During the installation of a new MRI machine, a technician started getting calls that iPhones weren’t…",
|
||||
"title": "iPhones Are Allergic to Helium",
|
||||
"author": "Kyle Wiens",
|
||||
"date": "2025-09-26T16:18:07-07:00",
|
||||
"website": "iFixit",
|
||||
"auto": true
|
||||
},
|
||||
"https://data.london.gov.uk/dataset/london-underground-average-monthly-temperatures/": {
|
||||
"excerpt": "Created 7 years ago, updated 5 months ago",
|
||||
"title": "London Underground Average Monthly Temperatures – London Datastore",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://www.goodreads.com/book/show/59593576-venomous-lumpsucker": {
|
||||
"excerpt": "A dark and witty story of environmental collapse and ru…",
|
||||
"title": "Venomous Lumpsucker",
|
||||
"author": "Ned Beauman14 books388 followersFollowFollow",
|
||||
"date": null,
|
||||
"website": "Goodreads",
|
||||
"auto": true
|
||||
},
|
||||
"https://en.wikipedia.org/wiki/Hundreds_of_Beavers": {
|
||||
"excerpt": "",
|
||||
"title": "Hundreds of Beavers",
|
||||
"author": "Contributors to Wikimedia projects",
|
||||
"date": "2024-02-28T21:58:49Z",
|
||||
"website": "Wikimedia Foundation, Inc.",
|
||||
"auto": true
|
||||
},
|
||||
"https://en.wikipedia.org/wiki/List_of_tallest_structures": {
|
||||
"excerpt": "From Wikipedia, the free encyclopedia",
|
||||
"title": "List of tallest structures",
|
||||
"author": "Contributors to Wikimedia projects",
|
||||
"date": "2003-01-07T22:54:29Z",
|
||||
"website": "Wikimedia Foundation, Inc.",
|
||||
"auto": true
|
||||
},
|
||||
"https://asteriskmag.com/issues/05/lies-damned-lies-and-manometer-readings": {
|
||||
"excerpt": "America’s HVAC labor force is plagued by dishonesty and frequently incapable of meeting industry standards. Interventions in indoor air quality are the next frontier in pandemic prevention — but are they up to the task?",
|
||||
"title": "Lies, Damned Lies, and Manometer Readings—Asterisk",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://www.worksinprogress.news/p/flipping-the-switch-on-far-uvc": {
|
||||
"excerpt": "We’ve known about far-UVC’s promise for a decade. Why isn't it everywhere?",
|
||||
"title": "Flipping the switch on far-UVC",
|
||||
"author": "Richard Williamson",
|
||||
"date": "2025-03-10T13:55:11+00:00",
|
||||
"website": "The Works in Progress Newsletter",
|
||||
"auto": true
|
||||
},
|
||||
"https://www.directdebit.co.uk/": {
|
||||
"excerpt": "Welcome to the home of Direct Debit, the UK's favourite way to make payments automatically.",
|
||||
"title": "Direct Debit",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://www.legislation.gov.uk/uksi/2017/752/regulation/77": {
|
||||
"excerpt": "These Regulations transpose in part Directive 2015/2366/EU of the European Parliament and of the Council of 25th November 2015 on payment services in the internal market, amending Directives 2002/65/EC, 2009/110/EC and 2013/36/EU and Regulation (EU) No. 1093/2010, and repealing Directive 2007/64/EC (OJ L 337 23.12.2015, p.35) also known as the Revised Payment Services Directive or “PSD2”. The Financial Conduct Authority (“FCA”) is responsible for transposing other parts of PSD2. A transposition note setting out how PSD2 will be transposed into UK law is published with the Explanatory Memorandum to these Regulations on legislation.gov.uk.",
|
||||
"title": "The Payment Services Regulations 2017",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://www.bitsaboutmoney.com/": {
|
||||
"excerpt": "Biweekly newsletter about intersection of tech and finance. Deep dives into the plumbing that moves money and the businesses that build those pipes.",
|
||||
"title": "Bits about Money (@patio11)",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": "Bits about Money",
|
||||
"auto": true
|
||||
},
|
||||
"https://stripe.com/gb/legal/acquirer-disclosure": {
|
||||
"excerpt": "Acquirer Disclosure",
|
||||
"title": "Acquirer Disclosure",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://en.wikipedia.org/wiki/EMV": {
|
||||
"excerpt": "EMV is a payment method based on a technical standard for smart payment cards and for payment terminals and automated teller machines which can accept them. EMV stands for \"Europay, Mastercard, and Visa\", the three companies that created the standard.[1]",
|
||||
"title": "EMV",
|
||||
"author": "Contributors to Wikimedia projects",
|
||||
"date": "2004-02-07T11:40:40Z",
|
||||
"website": "Wikimedia Foundation, Inc.",
|
||||
"auto": true
|
||||
},
|
||||
"https://www.bitsaboutmoney.com/archive/how-credit-cards-make-money/": {
|
||||
"excerpt": "Credit cards make money through net interest, interchange, fees, and marketing contributions.",
|
||||
"title": "How credit cards make money",
|
||||
"author": "Patrick McKenzie (patio11)",
|
||||
"date": "2021-11-05T16:05:00.000Z",
|
||||
"website": "Bits about Money",
|
||||
"auto": true
|
||||
},
|
||||
"https://en.wikipedia.org/wiki/Durbin_amendment": {
|
||||
"excerpt": "From Wikipedia, the free encyclopedia",
|
||||
"title": "Durbin amendment",
|
||||
"author": "Contributors to Wikimedia projects",
|
||||
"date": "2013-08-22T10:10:48Z",
|
||||
"website": "Wikimedia Foundation, Inc.",
|
||||
"auto": true
|
||||
},
|
||||
"https://www.mastercard.com/us/en/business/support/merchant-surcharge-rules.html": {
|
||||
"excerpt": "Mastercard credit card surcharge rules and fees for merchants are based on product type and merchant category. Learn about disclosure requirements, surcharge caps and more.",
|
||||
"title": "Mastercard Credit Card Surcharge Rules and Fees for Merchants",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": "Mastercard",
|
||||
"auto": true
|
||||
},
|
||||
"https://www.psr.org.uk/": {
|
||||
"excerpt": "PSR works to make payment systems accessible, reliable, and fair. We promote competition, innovation, and protection for payment system users in the UK.",
|
||||
"title": "Home",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://www.graphcore.ai/posts/graphcore-joins-softbank-group-to-build-next-generation-of-ai-compute": {
|
||||
"excerpt": "Graphcore today announced that the company has been acquired by SoftBank Group.",
|
||||
"title": "Graphcore joins SoftBank Group to build next generation of AI compute",
|
||||
"author": "Nigel Toon",
|
||||
"date": "2024-07-11T22:59:06.000Z",
|
||||
"website": "Graphcore",
|
||||
"auto": true
|
||||
},
|
||||
"https://www.ft.com/content/e33bab13-2d64-47f7-b0e2-9ba446296234": {
|
||||
"excerpt": "Deal will give Bristol-based company a resource boost while advancing the ‘next big bet’ of Masayoshi Son’s group",
|
||||
"title": "SoftBank buys UK chipmaker Graphcore in AI push",
|
||||
"author": "Tim Bradshaw, Ivan Levingston, David Keohane",
|
||||
"date": "2024-07-11T23:01:29.403Z",
|
||||
"website": "Financial Times",
|
||||
"auto": true
|
||||
},
|
||||
"https://sifted.eu/articles/graphcore-cofounder-exits-company-one-year-on-from-softbank-acquisition": {
|
||||
"excerpt": "The departure follows the Japanese multinational buying the struggling Bristol-based chip maker in July last year",
|
||||
"title": "Graphcore cofounder exits company one year on from SoftBank acquisition | Sifted",
|
||||
"author": "Kai Nicol-Schwarz",
|
||||
"date": null,
|
||||
"website": "Sifted",
|
||||
"auto": true
|
||||
},
|
||||
"https://en.wikipedia.org/wiki/Barrel_processor": {
|
||||
"excerpt": "From Wikipedia, the free encyclopedia",
|
||||
"title": "Barrel processor",
|
||||
"author": "Contributors to Wikimedia projects",
|
||||
"date": "2004-12-14T01:32:04Z",
|
||||
"website": "Wikimedia Foundation, Inc.",
|
||||
"auto": true
|
||||
},
|
||||
"https://shape-of-code.com/2022/11/20/stochastic-rounding-reemerges/": {
|
||||
"excerpt": "Just like integer types, floating-point types are capable of representing a finite number of numeric values. An important difference between integer and floating types is that the result of arithmetic and relational operations using integer types is exactly representable in an integer type (provided they don’t overflow), while the result of arithmetic operations using floating types may not be exactly representable in the corresponding floating type.",
|
||||
"title": "The Shape of Code » Stochastic rounding reemerges",
|
||||
"author": "Derek Jones",
|
||||
"date": null,
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://www.nvidia.com/en-us/data-center/gb200-nvl72/": {
|
||||
"excerpt": "Discover the powerful GB200 NVL72 GPU, engineered for AI workloads and next-gen data centers.",
|
||||
"title": "NVIDIA GB200 NVL72",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": "NVIDIA",
|
||||
"auto": true
|
||||
},
|
||||
"https://research.colfax-intl.com/cutlass-tutorial-writing-gemm-kernels-using-tensor-memory-for-nvidia-blackwell-gpus/": {
|
||||
"excerpt": "The NVIDIA Blackwell architecture introduces some new features that significantly change the shape of a GEMM kernel. In this series of posts, we explore the new features available on Blackwell and …",
|
||||
"title": "CUTLASS Tutorial: Writing GEMM Kernels Using Tensor Memory For NVIDIA® Blackwell GPUs",
|
||||
"author": null,
|
||||
"date": "2025-04-19T16:00:33+00:00",
|
||||
"website": "Colfax Research",
|
||||
"auto": true
|
||||
},
|
||||
"https://hazyresearch.stanford.edu/blog/2024-05-12-tk": {
|
||||
"excerpt": "how make gpu fast?",
|
||||
"title": "GPUs Go Brrr",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://graphcore-research.github.io/publications/": {
|
||||
"excerpt": "The official Graphcore Research blog.",
|
||||
"title": "Our Papers",
|
||||
"author": "Graphcore Research",
|
||||
"date": null,
|
||||
"website": "Graphcore Research Blog",
|
||||
"auto": true
|
||||
},
|
||||
"https://sites.research.google/trc/about/": {
|
||||
"excerpt": "TPU Research Cloud by Google",
|
||||
"title": "TPU Research Cloud - About",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://www.uktech.news/deep-tech/graphcore-microsoft-deal-20221010": {
|
||||
"excerpt": "The landmark deal between Graphcore and Microsoft has fallen through, causing key investors in the UK firm to devalue their stake.",
|
||||
"title": "Graphcore loses Microsoft deal as key investors write down stake value",
|
||||
"author": "Oscar Hornstein",
|
||||
"date": "2022-10-10T10:33:56+00:00",
|
||||
"website": "UKTN",
|
||||
"auto": true
|
||||
},
|
||||
"https://www.gizchina.com/tech/tsmc-announces-its-first-3nm-ai-chip-customer-neither-apple-nor-huawei": {
|
||||
"excerpt": "TSMC announces its first 3nm AI chip customer - neither Apple nor Huawei. Graphcore Colossus will skip the 5nm process to launch a 3nm chip",
|
||||
"title": "TSMC announces its first 3nm AI chip customer - neither Apple nor Huawei",
|
||||
"author": "Efe Udin",
|
||||
"date": "2020-08-28T05:55:17.000Z",
|
||||
"website": "Gizchina",
|
||||
"auto": true
|
||||
},
|
||||
"https://arxiv.org/abs/2303.06865": {
|
||||
"excerpt": "The high computational and memory requirements of large language model (LLM) inference make it feasible only with multiple high-end accelerators. Motivated by the emerging demand for latency-insensitive tasks with batched processing, this paper initiates the study of high-throughput LLM inference using limited resources, such as a single commodity GPU. We present FlexGen, a high-throughput generation engine for running LLMs with limited GPU memory. FlexGen can be flexibly configured under various hardware resource constraints by aggregating memory and computation from the GPU, CPU, and disk. By solving a linear programming problem, it searches for efficient patterns to store and access tensors. FlexGen further compresses the weights and the attention cache to 4 bits with negligible accuracy loss. These techniques enable FlexGen to have a larger space of batch size choices and thus significantly increase maximum throughput. As a result, when running OPT-175B on a single 16GB GPU, FlexGen achieves significantly higher throughput compared to state-of-the-art offloading systems, reaching a generation throughput of 1 token/s for the first time with an effective batch size of 144. On the HELM benchmark, FlexGen can benchmark a 30B model with a 16GB GPU on 7 representative sub-scenarios in 21 hours. The code is available at https://github.com/FMInference/FlexGen",
|
||||
"title": "FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU",
|
||||
"author": "[Submitted on 13 Mar 2023 (v1), last revised 12 Jun 2023 (this version, v2)]",
|
||||
"date": null,
|
||||
"website": "arXiv.org",
|
||||
"auto": true
|
||||
},
|
||||
"https://docs.pytorch.org/tutorials/intermediate/FSDP_tutorial.html": {
|
||||
"excerpt": "PyTorch Documentation. Explore PyTorch, an open-source machine learning library that accelerates the path from research prototyping to production deployment. Discover tutorials, API references, and guides to help you build and deploy deep learning models efficiently.",
|
||||
"title": "Getting Started with Fully Sharded Data Parallel (FSDP2)",
|
||||
"author": "PyTorch Contributors",
|
||||
"date": "2023-01-01T00:00:00Z",
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://www.servethehome.com/hands-on-with-a-graphcore-c2-ipu-pcie-card-at-dell-tech-world/": {
|
||||
"excerpt": "We were able to get our hands on a Graphcore C2 IPU PCIe card at Dell Technologies World 2019 to show one of the hottest pieces of AI and deep learning tech",
|
||||
"title": "Hands-on With a Graphcore C2 IPU PCIe Card at Dell Tech World",
|
||||
"author": "Patrick Kennedy",
|
||||
"date": "2019-06-07T15:45:33+00:00",
|
||||
"website": "ServeTheHome",
|
||||
"auto": true
|
||||
},
|
||||
"https://docs.graphcore.ai/projects/C600-datasheet/en/latest/overview.html": {
|
||||
"excerpt": "The Graphcore® C600 IPU-Processor card is a dual-slot, full-height PCI Express Gen4 card containing Graphcore’s Mk2 IPU with FP8 support, designed to accelerate machine intelligence applications for both training and inference. All other components are supplied by industry-standard vendors. GC-C600 is the regulatory model for the C600 PCIe card.",
|
||||
"title": "1. Overview — C600 Datasheet",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://www.eetimes.com/graphcore-supercharges-ipu-with-wafer-on-wafer/": {
|
||||
"excerpt": "Graphcore Bow IPU AI processor, the first commercial WoW chip, boosts performance up to 40% using same design",
|
||||
"title": "Graphcore Supercharges IPU with Wafer-on-Wafer",
|
||||
"author": "Sally Ward-Foxton",
|
||||
"date": "2022-03-03T10:00:04+00:00",
|
||||
"website": "EE Times",
|
||||
"auto": true
|
||||
},
|
||||
"https://www.graphcore.ai/posts/simple-fp16-and-fp8-training-with-unit-scaling": {
|
||||
"excerpt": "Unit Scaling is a new low-precision machine learning method able to train language models in FP16 and FP8 without loss scaling.",
|
||||
"title": "Simple FP16 and FP8 training with unit scaling",
|
||||
"author": "Charlie Blake",
|
||||
"date": "2023-03-29T10:38:56.000Z",
|
||||
"website": "Graphcore",
|
||||
"auto": true
|
||||
},
|
||||
"https://en.wikipedia.org/wiki/Second_law_of_thermodynamics": {
|
||||
"excerpt": "The second law of thermodynamics is a physical law based on universal empirical observation concerning heat and energy interconversions. A simple statement of the law is that heat always flows spontaneously from hotter to colder regions of matter (or 'downhill' in terms of the temperature gradient). Another statement is: \"Not all heat can be converted into work in a cyclic process.\"[1][2][3] These are informal definitions, however; more formal definitions appear below.",
|
||||
"title": "Second law of thermodynamics",
|
||||
"author": "Contributors to Wikimedia projects",
|
||||
"date": "2002-10-24T19:45:24Z",
|
||||
"website": "Wikimedia Foundation, Inc.",
|
||||
"auto": true
|
||||
},
|
||||
"https://github.com/osmarks/gc-kernel-module-patch/": {
|
||||
"excerpt": "Graphcore kernel driver patched for modern kernels - osmarks/gc-kernel-module-patch",
|
||||
"title": "GitHub - osmarks/gc-kernel-module-patch: Graphcore kernel driver patched for modern kernels",
|
||||
"author": "osmarks",
|
||||
"date": null,
|
||||
"website": "GitHub",
|
||||
"auto": true
|
||||
},
|
||||
"https://github.com/osmarks/IPUpy-patch": {
|
||||
"excerpt": "jndean IPUpy patched for C600. Contribute to osmarks/IPUpy-patch development by creating an account on GitHub.",
|
||||
"title": "GitHub - osmarks/IPUpy-patch: jndean IPUpy patched for C600",
|
||||
"author": "osmarks",
|
||||
"date": null,
|
||||
"website": "GitHub",
|
||||
"auto": true
|
||||
},
|
||||
"https://github.com/jndean/IPUDOOM": {
|
||||
"excerpt": "DOOM (1993) ported to run on the IPU 👿. Contribute to jndean/IPUDOOM development by creating an account on GitHub.",
|
||||
"title": "GitHub - jndean/IPUDOOM: DOOM (1993) ported to run on the IPU 👿",
|
||||
"author": "jndean",
|
||||
"date": null,
|
||||
"website": "GitHub",
|
||||
"auto": true
|
||||
},
|
||||
"https://docs.graphcore.ai/projects/command-line-tools/en/latest/introduction.html": {
|
||||
"excerpt": "Note: Searching from the top-level index page will search all documents. Searching from a specific document will search only that document.",
|
||||
"title": "1. Introduction — Graphcore Command Line Tools",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://huggingface.co/google/siglip-so400m-patch14-384": {
|
||||
"excerpt": "We’re on a journey to advance and democratize artificial intelligence through open source and open science.",
|
||||
"title": "google/siglip-so400m-patch14-384 · Hugging Face",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://github.com/mlfoundations/open_clip/blob/main/docs/model_profile.csv": {
|
||||
"excerpt": "An open source implementation of CLIP. Contribute to mlfoundations/open_clip development by creating an account on GitHub.",
|
||||
"title": "open_clip/docs/model_profile.csv at main · mlfoundations/open_clip",
|
||||
"author": "mlfoundations",
|
||||
"date": null,
|
||||
"website": "GitHub",
|
||||
"auto": true
|
||||
},
|
||||
"https://docs.graphcore.ai/projects/ipu-programmers-guide/en/latest/about_ipu.html": {
|
||||
"excerpt": "The IPU is based on a highly parallel architecture designed to accelerate\nmachine learning applications. It provides very high floating-point performance\non mixed-precision floating-point data. The floating-point calculations are performed in\neither IEEE 754 single-precision floating-point or half-precision floating-point. The white paper contains details about all aspects of IPU floating-point number representation and arithmetic.",
|
||||
"title": "2. IPU hardware overview — IPU Programmer's Guide",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": null,
|
||||
"auto": true
|
||||
},
|
||||
"https://github.com/graphcore/PopRT": {
|
||||
"excerpt": "Contribute to graphcore/PopRT development by creating an account on GitHub.",
|
||||
"title": "GitHub - graphcore/PopRT",
|
||||
"author": "graphcore",
|
||||
"date": null,
|
||||
"website": "GitHub",
|
||||
"auto": true
|
||||
},
|
||||
"https://github.com/graphcore/poptorch": {
|
||||
"excerpt": "PyTorch interface for the IPU. Contribute to graphcore/poptorch development by creating an account on GitHub.",
|
||||
"title": "GitHub - graphcore/poptorch: PyTorch interface for the IPU",
|
||||
"author": "graphcore",
|
||||
"date": null,
|
||||
"website": "GitHub",
|
||||
"auto": true
|
||||
},
|
||||
"https://github.com/graphcore-research/flash-attention-ipu": {
|
||||
"excerpt": "Poplar implementation of FlashAttention for IPU. Contribute to graphcore-research/flash-attention-ipu development by creating an account on GitHub.",
|
||||
"title": "GitHub - graphcore-research/flash-attention-ipu: Poplar implementation of FlashAttention for IPU",
|
||||
"author": "graphcore-research",
|
||||
"date": null,
|
||||
"website": "GitHub",
|
||||
"auto": true
|
||||
},
|
||||
"https://github.com/graphcore-research/flash-attention-ipu/blob/main/demo/train.py": {
|
||||
"excerpt": "Poplar implementation of FlashAttention for IPU. Contribute to graphcore-research/flash-attention-ipu development by creating an account on GitHub.",
|
||||
"title": "flash-attention-ipu/demo/train.py at main · graphcore-research/flash-attention-ipu",
|
||||
"author": "graphcore-research",
|
||||
"date": null,
|
||||
"website": "GitHub",
|
||||
"auto": true
|
||||
},
|
||||
"https://arxiv.org/abs/2503.11901v3": {
|
||||
"excerpt": "This study characterizes GPU resilience in Delta HPC, a large-scale AI system that consists of 1,056 A100 and H100 GPUs, with over 1,300 petaflops of peak throughput. Delta HPC is operated by the National Center for Supercomputing Applications (NCSA) at the University of Illinois Urbana-Champaign. We used 2.5 years of operational data (11.7 million GPU hours) on GPU errors. Our major findings include: (i) H100 GPU memory resilience is worse than A100 GPU memory, with 3.2x lower per-GPU MTBE for memory errors, (ii) The GPU memory error-recovery mechanisms on H100 GPUs are insufficient to handle the increased memory capacity, (iii) H100 GPUs demonstrate significantly improved GPU hardware resilience over A100 GPUs with respect to critical hardware components, (iv) GPU errors on both A100 and H100 GPUs frequently result in job failures due to the lack of robust recovery mechanisms at the application level, and (v) We project the impact of GPU node availability on larger-scales and find that significant overprovisioning of 5% is necessary to handle GPU failures.",
|
||||
"title": "Characterizing GPU Resilience and Impact on AI/HPC Systems",
|
||||
"author": null,
|
||||
"date": null,
|
||||
"website": "arXiv.org",
|
||||
"auto": true
|
||||
},
|
||||
"https://www.graphcore.ai/posts/accelerating-resnet50-training-on-the-ipu-behind-our-mlperf-benchmark": {
|
||||
"excerpt": "Graphcore researchers and engineers explain how they achieved dramatic performance results for the popular computer vision model.",
|
||||
"title": "Accelerating ResNet-50 Training on the IPU for MLPerf",
|
||||
"author": "Dr. Mario Michael Krell, Zhenying Liu, Emmanuel Menage, and Bartosz Bogdanski",
|
||||
"date": "2022-01-17T09:07:39.000Z",
|
||||
"website": "Graphcore",
|
||||
"auto": true
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user