Stars
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
SWE-bench: Can Language Models Resolve Real-world Github Issues?
Ergonomic and modular web framework built with Tokio, Tower, and Hyper
Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.
Accelerate LLM preference tuning via prefix sharing with a single line of code
Sample Solana on-chain arbitrage bot
⚡️ TypeScript Execute | The easiest way to run TypeScript in Node.js
a solana dex arbitrage bot based on Jupiter v6
Optimizing SGEMM kernel functions on NVIDIA GPUs to a close-to-cuBLAS performance.
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
pytest plugin for distributed testing and loop-on-failures testing modes.
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
Solana arbitrage bot with onchain calculation
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Python disk-backed cache (Django-compatible). Faster than Redis and Memcached. Pure-Python.
Claude Code to OpenAI API Proxy
aiomonitor is module that adds monitor and python REPL capabilities for asyncio application
Train transformer language models with reinforcement learning.
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling