willccbb

# train_grpo.py
#
# See https://github.com/willccbb/verifiers for ongoing developments
#
import re
import torch
from datasets import load_dataset, Dataset
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import LoraConfig
from trl import GRPOConfig, GRPOTrainer

pixelmager

2020

• https://miketuritzin.com/post/hierarchical-depth-buffers/
• https://developer.nvidia.com/blog/optimizing-compute-shaders-for-l2-locality-using-thread-group-id-swizzling/
• https://asawicki.info/news_1735_a_better_way_to_scalarize_a_shader

2019

• https://developer.download.nvidia.com/video/GDC-19/NSIGHT_GPU_TRACE_Bavoil.pdf (video)

2018

• https://anteru.net/blog/2018/intro-to-compute-shaders/index.html

TheRealMJP

// The following code is licensed under the MIT license: https://gist.github.com/TheRealMJP/bc503b0b87b643d3505d41eab8b332ae

// Samples a texture with Catmull-Rom filtering, using 9 texture fetches instead of 16.
// See http://vec3.ca/bicubic-filtering-in-fewer-taps/ for more details
float4 SampleTextureCatmullRom(in Texture2D<float4> tex, in SamplerState linearSampler, in float2 uv, in float2 texSize)
{
    // We're going to sample a a 4x4 grid of texels surrounding the target UV coordinate. We'll do this by rounding
    // down the sample location to get the exact center of our "starting" texel. The starting texel will be at
    // location [1, 1] in the grid, where [0, 0] is the top left corner.
    float2 samplePos = uv * texSize;