Skip to content
View hargup's full-sized avatar

Organizations

@AGV-IIT-KGP @metakgp @Azad-Hall

Block or report hargup

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

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

Report abuse

Starred repositories

Showing results
Rust 26 4 Updated Oct 28, 2026

reproducing the flapping airplanes megakernel, in collab with magni

Cuda 139 18 Updated Nov 8, 2026

Vx: one language, every chip.

Rust 251 36 Updated Nov 16, 2026

🧱 Experimental library for building inference engines

Python 434 37 Updated Nov 16, 2026

Sub-1-bit LLM compression (LittleBit / LittleBit-2) re-implemented in PyTorch, with an attention-sink-aware distillation loss. Qwen3-0.6B at 0.55 BPW: PPL 36.4 vs 21.0 on a GTX 1080.

Python 1 Updated Oct 23, 2026

Tokamax: A GPU and TPU kernel library.

Python 330 82 Updated Nov 16, 2026

High-performance safetensors model loader

Python 184 42 Updated Nov 16, 2026

Hardware as fast as software.

TypeScript 699 147 Updated Nov 11, 2026

A PyTorch native automated mega-kernel compiler

Python 38 13 Updated Nov 12, 2026

Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C infe…

Python 2,560 195 Updated Nov 12, 2026

LiteLLM, in Lean.

Lean 10 2 Updated Nov 8, 2026

Development repo for translating Software Foundations to Lean

Rocq Prover 210 62 Updated Nov 14, 2026

Optimized GPU compiler for LLM inference. Choose from a list of optimized recipes or optimize your own model via kernel fusion, autotuning, and advanced scheduling. Run benchmarks across different …

Python 125 20 Updated Nov 16, 2026

Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.

Python 1,626 165 Updated Nov 13, 2026

A local inference engine for Apple silicon, built around the model.

C++ 2,311 230 Updated Nov 11, 2026

Mixture-of-experts (MoE) training megakernel for NVL72s

Python 645 88 Updated Oct 1, 2026

A curated list of Lean 4 libraries, tools, frameworks and learning resources for programmers

22 3 Updated Oct 21, 2026

spur your compute

Rust 141 58 Updated Nov 16, 2026

A high-throughput and memory-efficient inference and serving engine for LLMs

Python 97,009 24,882 Updated Nov 16, 2026

Compile and run CUDA on Apple M4-M5 GPUs

C++ 78 11 Updated Nov 13, 2026
Lean 7 Updated Nov 7, 2026
Lean 14 1 Updated Nov 7, 2026

An independent implementation of the Lean 4 kernel on .NET, and a checker for Lean exports

C# 8 1 Updated Nov 8, 2026

High performance coding agent harness written in Rust, built for heavy multi-agent dev workflows

Rust 21,807 2,542 Updated Nov 16, 2026

A Rust framework for correct and performant distributed systems

Rust 1,568 109 Updated Nov 15, 2026

A unified CLI to connect artificial intelligence to the social web.

TypeScript 30 2 Updated Aug 24, 2026

why-did-you-render by Welldone Software monkey patches React to notify you about potentially avoidable re-renders. (Works with React Native as well.)

JavaScript 12,534 223 Updated Apr 15, 2026

Statically verify your layout code

TypeScript 686 12 Updated Sep 20, 2026

Shen extension that makes layout overflow a compile-time type error

JavaScript 9 Updated Sep 24, 2026

Halo is an open-source framework built by White Circle for training large language and multimodal models

Python 862 46 Updated Nov 15, 2026
Next