Skip to content
View dhcode-cpp's full-sized avatar
🐒
Making AI Safer
🐒
Making AI Safer

Block or report dhcode-cpp

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Code for the paper "Language Models are Unsupervised Multitask Learners"

Python 24,345 5,816 Updated Aug 14, 2024

[ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule

Python 357 21 Updated Sep 15, 2025

Collection of scripts and notebooks for OpenAI's latest GPT OSS models

Jupyter Notebook 473 50 Updated Aug 25, 2025

Flash Attention Triton kernel with support for second-order derivatives

Python 108 10 Updated Oct 21, 2025

Dion optimizer algorithm

Python 381 32 Updated Nov 1, 2025

Utility scripts for PyTorch (e.g. Make Perfetto show some disappearing kernels, Memory profiler that understands more low-level allocations such as NCCL, ...)

Python 64 5 Updated Sep 11, 2025

rl from zero pretrain, can it be done? yes.

Python 280 22 Updated Sep 28, 2025

Trainable fast and memory-efficient sparse attention

C++ 432 38 Updated Nov 6, 2025

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Python 19,118 1,906 Updated Nov 1, 2025

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

C++ 4,230 420 Updated Nov 6, 2025

Distribute and run LLMs with a single file.

C 23,338 1,234 Updated Nov 5, 2025

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

Python 928 77 Updated Sep 4, 2024

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

Python 7,789 599 Updated Oct 24, 2025
Python 149 12 Updated Oct 27, 2025

[Up-to-date] Awesome Agentic Deep Research Resources

529 46 Updated Aug 26, 2025

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

Python 1,142 97 Updated Oct 20, 2025

Copy-paste Liquid Glass shader with SVG

JavaScript 838 41 Updated Jun 11, 2025
Python 920 55 Updated Oct 20, 2025

Pipeline Parallelism Emulation and Visualization

Python 70 5 Updated Jun 12, 2025

A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.

Python 2,874 305 Updated Mar 10, 2025

General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]

Python 196 11 Updated Oct 29, 2025

Recreating PyTorch from scratch (C/C++, CUDA, NCCL and Python, with multi-GPU support and automatic differentiation!)

Python 160 11 Updated Jun 6, 2024

depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.

Python 753 26 Updated Oct 13, 2025

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

Python 2,803 90 Updated Nov 5, 2025

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Python 3,301 194 Updated Oct 25, 2025

Explore the Multimodal “Aha Moment” on 2B Model

Python 614 22 Updated Mar 18, 2025
Next