Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPU (github.com) | HN Screenshots

YHacker Newsscreenshots

Screenshot of github.com: Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPU

First screen, captured 8 months ago.

Looks similar

Screenshot of github.com: Tiny hackable CUDA language model implementation

Tiny hackable CUDA language model implementation (github.com)

72 points by markusheimerl 4 months ago | 13 comments

Screenshot of github.com: An SLM trained on $8 ESP32-S3

An SLM trained on $8 ESP32-S3 (github.com)

55 points by pavelai 2 months ago | 17 comments

Screenshot of github.com: High fidelity font synthesis for CJK languages

High fidelity font synthesis for CJK languages (github.com)

43 points by kaonashi-tyc-01 7 months ago | 4 comments

Screenshot of github.com: Zlob.h 100% POSIX and glibc compatible globbing lib that is faste and better

Zlob.h 100% POSIX and glibc compatible globbing lib that is faste and better (github.com)

17 points by neogoose 8 months ago | 10 comments

Screenshot of github.com: Show HN: ZXC – Asymmetric, +40% decode vs. LZ4 on ARM (C, BSD-3, Fuzzed)

Show HN: ZXC – Asymmetric, +40% decode vs. LZ4 on ARM (C, BSD-3, Fuzzed)(github.com)

15 points by pollop_ 10 months ago | 3 comments

Screenshot of github.com: Attyx – tiny and fast GPU-accelerated terminal emulator written in Zig

Attyx – tiny and fast GPU-accelerated terminal emulator written in Zig (github.com)

10 points by nicholasrq 8 months ago | 6 comments