zanussbaum / surfgrad
webgpu autograd library
☆22Updated 3 months ago
Alternatives and similar repositories for surfgrad:
Users that are interested in surfgrad are comparing it to the libraries listed below
- A tree-based prefix cache library that allows rapid creation of looms: hierarchal branching pathways of LLM generations.☆68Updated last month
- look how they massacred my boy☆63Updated 5 months ago
- LLM training in simple, raw C/Metal Shading Language☆49Updated 11 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆91Updated 3 weeks ago
- ☆38Updated 8 months ago
- TOPLOC: is a novel method for verifiable inference that enables users to verify that LLM providers are using the correct model configurat…☆17Updated last month
- implementation of https://arxiv.org/pdf/2312.09299☆20Updated 8 months ago
- Lego for GRPO☆25Updated 2 weeks ago
- ☆27Updated 8 months ago
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆63Updated 4 months ago
- WebGPU LLM inference tuned by hand☆149Updated last year
- smolLM with Entropix sampler on pytorch☆151Updated 5 months ago
- ☆97Updated 5 months ago
- Cerule - A Tiny Mighty Vision Model☆67Updated 6 months ago
- A collection of optimizers for MLX☆34Updated 2 weeks ago
- GPU accelerated client-side embeddings for vector search, RAG etc.☆66Updated last year
- research impl of Native Sparse Attention (2502.11089)☆53Updated last month
- This repository has code for fine-tuning LLMs with GRPO specifically for Rust Programming using cargo as feedback☆75Updated 3 weeks ago
- Standalone commandline CLI tool for compiling Triton kernels☆17Updated 6 months ago
- An example implementation of RLHF (or, more accurately, RLAIF) built on MLX and HuggingFace.☆25Updated 9 months ago
- DeMo: Decoupled Momentum Optimization☆185Updated 3 months ago
- RWKV-7: Surpassing GPT☆82Updated 4 months ago
- Latent Large Language Models☆17Updated 7 months ago
- trying to make WebGPU a bit easier to use☆16Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆39Updated last month
- Inference Llama 2 in one file of zero-dependency, zero-unsafe Rust☆37Updated last year
- Simple GRPO scripts and configurations.☆59Updated last month
- Because it's there.☆16Updated 6 months ago
- ☆33Updated 8 months ago
- train entropix like a champ!☆20Updated 5 months ago