Skip to content

Instantly share code, notes, and snippets.

View paulphys's full-sized avatar

paul paulphys

View GitHub Profile
@fxkamd
fxkamd / bert-tiny-amd.md
Created October 1, 2024 19:06
Solutions to problems with BERT training with tinygrad on AMD GPUs

Thank you to tiny corp for pointing out some problems running BERT training with Tinygrad on AMD GPUs in this Tweet. We had a few engineers at AMD take a look at the problem and they were quickly able to reproduce it.

What they found was an issue related to CWSR (compute wave save restore), which is a mechanism that allows our driver and firmware to preempt and reschedule long-running compute waves on our GPUs. The GFXv11 GPU line requires a workaround to set COMPUTE_PGM_RSRC1.PRIV=1 when dispatching a compute kernel. Normally this is handled by the AQL DISPATCH packet. However, since the Tinygrad implementation leverages a custom runtime, it requires this workaround in its PM4-based dispatch. This patch is specific to GFXv11 GPUs. Other GPUs do not require it and should not use this workaround. The following KFDTest patch can be used as a reference: https://github.com/ROCm/ROCT-Thunk-Interface/commit/507637ed5b82197eecbf483cdc1234939766549a

While inv

@fragtion
fragtion / configuration.yml
Created September 24, 2023 01:52
leetify-cs2-stats-home-assistant
sensor:
- platform: rest
name: leetify
resource: https://api.leetify.com/api/profile/76561197990921651 #replace the profile id with your own profile id, from eg: https://api.leetify.com/api/profile/76561197990921651
json_attributes:
- games
- recentGameRatings
value_template: 'OK'
scan_interval: 600
- platform: template
@scyto
scyto / proxmox.md
Last active April 30, 2025 08:28
my proxmox cluster

ProxMox Cluster - Soup-to-Nutz

aka what i did to get from nothing to done.

note: these are designed to be primarily a re-install guide for myself (writing things down helps me memorize the knowledge), as such don't take any of this on blind faith - some areas are well tested and the docs are very robust, some items, less so). YMMV

Purpose of Proxmox cluster project

Required Outomces of cluster project

@ConcurrentSquared
ConcurrentSquared / KCI_FI0029552691024_1.jpg
Last active September 29, 2023 20:12
LK-99 paper (Korean Journal of Crystal Growth) machine translation (Google) to English
KCI_FI0029552691024_1.jpg
@hibobmaster
hibobmaster / README.md
Last active April 14, 2025 08:15
Matrix (dendrite + element-web) in Docker with Traefik and federation

project structure

.
├── compose.yaml
├── config
│   └── dendrite.yaml
├── element-web
│   └── config.json
├── nginx
│   └── dendrite.conf
@nivethan-me
nivethan-me / README.md
Last active December 4, 2024 03:49
Setup a Next.js 13 project with Eslint + Prettier with automatic tailwind class sorting

Accounts I follow on YouTube

Got it from running below script:

let markdown = Array.from(document.querySelectorAll("ytd-channel-renderer"))
  .map((item) => ({
    title: item.querySelector("#text-container").textContent.trim(),
    url: item.querySelector("#main-link").href,
 }))
@degitgitagitya
degitgitagitya / .env
Last active April 28, 2025 06:34
Next JS + Next Auth + Keycloak + AutoRefreshToken
# KEYCLOAK BASE URL
KEYCLOAK_BASE_URL=
# KEYCLOAK CLIENT SECRET
KEYCLOAK_CLIENT_SECRET=
# KEYCLOAK CLIENT ID
KEYCLOAK_CLIENT_ID=
# BASE URL FOR NEXT AUTH