<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
    <title>distributed-computing</title>
    <link rel="self" type="application/atom+xml" href="https://links.biapy.com/guest/tags/3066/feed"/>
    <updated>2026-10-21T08:08:08+00:00</updated>
    <id>https://links.biapy.com/guest/tags/3066/feed</id>
            <entry>
            <id>https://links.biapy.com/links/13970</id>
            <title type="text"><![CDATA[Higgsfield]]></title>
            <link rel="alternate" href="https://github.com/higgsfield-ai/higgsfield" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13970"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters.]]>
            </summary>
            <updated>2026-09-21T12:22:40+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13384</id>
            <title type="text"><![CDATA[Petals]]></title>
            <link rel="alternate" href="https://petals.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13384"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Run LLMs at home, BitTorrent-style.

 You load a part of the model, then join a network of people serving its other parts. Single‑batch inference runs at up to 6 tokens/sec for Llama 2 (70B) and up to 4 tokens/sec for Falcon (180B) — enough for chatbots and interactive apps. 

- [Petals @ GitHub](https://github.com/bigscience-workshop/petals).]]>
            </summary>
            <updated>2026-07-23T11:49:42+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13378</id>
            <title type="text"><![CDATA[Mesh LLM]]></title>
            <link rel="alternate" href="https://meshllm.cloud/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13378"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat. 

Mesh LLM pools GPUs and memory across machines and exposes the result as one OpenAI-compatible API at http://localhost:9337/v1. Start one node, add more nodes later, and let the mesh decide whether a model runs locally, routes to a peer, or uses Skippy stage splits for models that are too large for one box.

- [Mesh LLM @ GitHub](https://github.com/Mesh-LLM/mesh-llm).]]>
            </summary>
            <updated>2026-07-23T06:34:13+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13224</id>
            <title type="text"><![CDATA[Talos worker]]></title>
            <link rel="alternate" href="https://usetalos.xyz/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13224"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[GPU worker client for the Talos network. Pairs with your Talos account, serves open-model inference jobs over a WebSocket, and reports uptime for payouts. 

- [Talos worker @ GitHub](https://github.com/jmerelnyc/Talos).]]>
            </summary>
            <updated>2026-07-06T11:31:40+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13093</id>
            <title type="text"><![CDATA[Shard]]></title>
            <link rel="alternate" href="https://github.com/leyten/shard" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13093"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Pipeline-parallel LLM inference across GPUs on separate machines.

Pipeline-parallel LLM inference across GPUs on separate machines. A model too large for any single card is split into contiguous blocks of layers — one shard per GPU — and a request is served by streaming activations through the shards in order. No datacenter, no single host, and no node ever holds the whole model.]]>
            </summary>
            <updated>2026-06-23T06:23:33+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/8482</id>
            <title type="text"><![CDATA[BOINC]]></title>
            <link rel="alternate" href="http://boinc.berkeley.edu/index.php" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/8482"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Use the idle time on your computer (Windows, Mac, Linux, or Android) to cure diseases, study global warming, discover pulsars, and do many other types of scientific research. It&amp;#039;s safe, secure, and easy:]]>
            </summary>
            <updated>2025-08-29T15:32:33+00:00</updated>
        </entry>
    </feed>
