overlast's Stars
huggingface/optimum-amd
AMD related optimizations for transformer models
microsoft/vidur
A large-scale simulation framework for LLM inference
microsoft/LLMLingua
To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
facebookresearch/sapiens
High-resolution models for human tasks.
joisino/laf
Code for "Training-free Graph Neural Networks and the Power of Labels as Features" (TMLR 2024)
triton-lang/triton
Development repository for the Triton language and compiler
0burak/imperial_hft
exo-explore/exo
Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚
AnswerDotAI/gpu.cpp
A lightweight library for portable low-level GPU computation using WebGPU.
sarulab-speech/spatial_voice_conversion
Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals
karpathy/LLM101n
LLM101n: Let's build a Storyteller
facebookresearch/chameleon
Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
karpathy/llm.c
LLM training in simple, raw C/CUDA
facebookresearch/MemoryMosaics
Memory Mosaics are networks of associative memories working in concert to achieve a prediction task.
HojiChar/HojiChar
The robust text processing pipeline framework enabling customizable, efficient, and metric-logged text preprocessing.
danielplohmann/mcrit
The MinHash-based Code Relationship & Investigation Toolkit (MCRIT) is a framework created to simplify the application of the MinHash algorithm in the context of code similarity.
jqlang/jq
Command-line JSON processor
inspection-ai/japanese-toxic-dataset
spmtrx/spmtrx
spmtrx/lprp
yoquankara/interpret_p_tuning
Source code for paper "Interpretability in Continuous Prompt Tuning for Japanese Generative Pre-trained Transformers"
tuem/trimatch
Trimatch: An (Exact|Prefix|Approximate) String Matching Library
tuem/sftrie
A compact trie representation
estraier/tkrzw
a set of implementations of DBM
facebookresearch/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
microsoft/Web-Dev-For-Beginners
24 Lessons, 12 Weeks, Get Started as a Web Developer
Homebrew/install
📥 Homebrew (un)installer
IsabelMeraner/BotanicalNER
Named entity recognition for scientific and vernacular plant names
WorksApplications/SudachiDict
A lexicon for Sudachi
jacobeisenstein/gt-nlp-class
Course materials for Georgia Tech CS 4650 and 7650, "Natural Language"