corpus.blog
41554 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a087b0-a346-7212-a55e-fa046f22f2d3

Implementing Character.AI’s memory optimizations in nanoGPT

njkumar.com · published 20 January 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 njkumar.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
16
Words captured
8,630

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://research.character.ai/optimizing-inference/
research.character.ai
https://github.com/karpathy/nanoGPT
github.com
Calculating GPT-2’s inference speedups Read at the source ↗
njkumar.com
https://arxiv.org/pdf/2305.13245
arxiv.org
https://x.com/YiTayML/status/1779903968057102438?lang=en
x.com
You could have designed state of the art Positional Encoding Read at the source ↗
fleetwood.dev
https://arxiv.org/pdf/2310.06825
arxiv.org
https://pytorch.org/blog/flexattention/
pytorch.org
https://arxiv.org/pdf/2405.12981
arxiv.org
https://arxiv.org/pdf/2410.18517
arxiv.org
https://arxiv.org/pdf/2405.14366
arxiv.org
https://www.youtube.com/watch?v=l8pRSuU81PU
youtube.com
https://lmsys.org/blog/2024-01-17-sglang/
lmsys.org
https://research.character.ai/optimizing-ai-inference-at-character-ai-part-deux/
research.character.ai
https://github.com/google/aqt
github.com
https://github.com/pytorch/ao/tree/main/torchao/prototype/quantized_training
github.com