corpus.blog
41,715 blogs · 5,239,565 posts Claim your blog
Record · corpus.blog/posts/01a08c59-e015-713c-8022-885820f13132

NanoGPT Speedrun Worklog

tylerromero.com · published 8 March 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 tylerromero.com Wayback capture
1blogs citing
First cited
5 Nov 2025
Most recent
5 Nov 2025
Rank this month
not ranked
External links
49
Words captured
2,505

Cited by

Blog
In the post
Date
nanx.me
Reverse dependency check speedrun: a data.table case study Read at the source ↗
5 Nov 2025

Links from this post

Link
Host
https://x.com/kellerjordan0/status/1859331370268623321
x.com
https://x.com/kellerjordan0/status/1842300916864844014
x.com
https://x.com/kellerjordan0/status/1876048851158880624
x.com
https://x.com/hi_tysam/status/1879687807678959729
x.com
https://x.com/kellerjordan0
x.com
https://x.com/hi_tysam
x.com
https://x.com/KoszarskyB
x.com
https://x.com/kellerjordan0/status/1798863559243513937
x.com
https://github.com/KellerJordan/modded-nanogpt?tab=readme-ov-file
github.com
https://github.com/tyler-romero/nanogpt-speedrun
github.com
https://github.com/tyler-romero/nanogpt-speedrun/commit/b3c32f8937c1f4655c5eb9607970e03e351a6c08
github.com
https://github.com/tyler-romero/nanogpt-speedrun/blob/main/logs/4c627c0d-029c-4f8a-bd18-40f99b43b22e.txt
github.com
https://github.com/tyler-romero/nanogpt-speedrun/commit/b7bb93fd988d73a55184c553f0020feec1454340
github.com
https://github.com/tyler-romero/nanogpt-speedrun/blob/main/logs/14fcdb07-443d-4d1c-b307-061bc4bd2cd6.txt
github.com
https://github.com/tyler-romero/nanogpt-speedrun/commit/b91c2c00673b125944abde277dd5ef3dc141284d
github.com
https://github.com/tyler-romero/nanogpt-speedrun/blob/main/logs/59951c17-fbe5-4577-a1bc-6dc0c1802d2e.txt
github.com
https://github.com/tyler-romero/nanogpt-speedrun/commit/d59944dbe8535fea8ea107d9a6fb133de5346de5
github.com
https://github.com/tyler-romero/nanogpt-speedrun/blob/main/logs/08047f73-cb01-4f47-a901-de901b2a6b6e.txt
github.com
https://github.com/tyler-romero/nanogpt-speedrun/commit/12eab44ca1bce8783a3b4d43bfef357eff1a652e
github.com
https://github.com/tyler-romero/nanogpt-speedrun/blob/main/logs/2dbf7fa6-561c-49bc-8aae-665fefdd9a44.txt
github.com
https://github.com/tyler-romero/nanogpt-speedrun/commit/d982ed5900922e43a266c5d671b88f36efe72aaf
github.com
https://github.com/tyler-romero/nanogpt-speedrun/blob/main/logs/cf1ef5f9-9f79-4798-9360-2b174d8eb25f.txt
github.com
https://github.com/karpathy/llm.c/blob/7b929300217ff1a974b63791a228928b39b26409/train_gpt2.py
github.com
https://github.com/karpathy/llm.c
github.com
https://github.com/KellerJordan/modded-nanogpt/tree/master?tab=readme-ov-file
github.com
https://arxiv.org/abs/2104.09864
arxiv.org
https://www.jitx.io/posts/rope-embeddings
jitx.io
Rotary Embeddings: A Relative Revolution Read at the source ↗
blog.eleuther.ai
https://arxiv.org/pdf/2109.08668
arxiv.org
https://arxiv.org/abs/2405.18392
arxiv.org
https://en.wikipedia.org/wiki/Downstream_(software_development
en.wikipedia.org
https://github.com/KellerJordan/modded-nanogpt
github.com
https://kellerjordan.github.io/posts/muon/
kellerjordan.github.io
https://x.com/leloykun/status/1846842883967692926
x.com
https://arxiv.org/abs/2409.20325v1
arxiv.org
https://arxiv.org/abs/1802.09568
arxiv.org
https://github.com/KellerJordan/modded-nanogpt/tree/master/records/102924_Optimizers
github.com
Deriving Muon Read at the source ↗
jeremybernste.in
https://storage.googleapis.com/deepmind-media/gemma/gemma-2-report.pdf
storage.googleapis.com
https://x.com/Grad62304977
x.com
FlexAttention: The Flexibility of PyTorch with the Performance of FlashAttention Read at the source ↗
pytorch.org
https://huggingface.co/docs/text-generation-inference/en/conceptual/flash_attention
huggingface.co
https://arxiv.org/abs/2409.20325
arxiv.org
https://arxiv.org/abs/2412.05496
arxiv.org
https://github.com/tysam-code/hlb-gpt
github.com
https://arxiv.org/abs/2203.15556
arxiv.org
https://web.archive.org/web/20250122060345/https://kellerjordan.github.io/posts/muon/
web.archive.org
https://arxiv.org/abs/2109.08668
arxiv.org
https://arxiv.org/abs/2408.00118
arxiv.org