Jackmin801/even-g2-fact-checker
Even Realities G2 fact-check card prototype
Machines teach me how to learn
Repositories
Jackmin801/autorebaser
Jackmin801/skillsbench
Jackmin801/rlm
Jackmin801/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Jackmin801/hf-blog
Public repo for HF blog posts
Jackmin801/cutlass
CUDA Templates and Python DSLs for High-Performance Linear Algebra
Jackmin801/inference-benchmark-skill
Jackmin801/pinyin-extension
Jackmin801/prime
Official CLI and Python SDK for Prime Intellect - access GPU compute, remote sandboxes, RL environments, and distributed training infrastructure for AI development at scale.
Jackmin801/nixl
NVIDIA Inference Xfer Library (NIXL)
Jackmin801/prime-rl-hardfork
Jackmin801/dynamo
A Datacenter Scale Distributed Inference Serving Framework
Jackmin801/vllm-omni
A framework for efficient model inference with omni-modality models
Jackmin801/flash-attention
Jackmin801/SnapViewer
PyTorch memory allocation visualizer
Jackmin801/flash-attention-dao-fork
Fast and memory-efficient exact attention
Jackmin801/torchtune
A Native-PyTorch Library for LLM Fine-tuning
Jackmin801/torchft
PyTorch per step fault tolerance (actively under development)
Jackmin801/torchtitan
A PyTorch native platform for training generative AI models
Jackmin801/DeFi-Bench
Environments to evaluate agentic capabilities in DeFi workflows
Jackmin801/DeLoop
Jackmin801/deepscaler
Democratizing Reinforcement Learning for LLMs
Jackmin801/PageRankVaccination
Code that implements Page Rank as a vaccination strategy and simulates the disease to measure effectiveness
Jackmin801/DS-Assignment-2022
Jackmin801/SVIP_LLM_Inference_Verification
Jackmin801/sglang
SGLang is a fast serving framework for large language models and vision language models.
Jackmin801/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.