#
ElenaViewSynthesis
Follow
Lists (32)
ADriving
SLAM36 repositories
Agents - RAGs - Coding Assistan
111 repositories
ARC - Abstraction in LLMs
Abstract Reasoning vs Scale, Francois Chollet6 repositories
Catastrophic Forget, DataLeakage
1 repository
Cloud
1 repository
CUDA - GPU kernels- JAX -Tensors
Compilers, HPC, TPU, GPU recipes, MLX, gradient processing,64 repositories
Diffusion - FlowMatch - Shortcut
26 repositories
Distributed, Tensor Parallelism
+ DeepSpeed, Ray.io19 repositories
Domain Gneralization, LongContex
1 repository
Edge LLMs
Tiny agents,17 repositories
GPTs & Llama variants
35 repositories
GS-SfM - Colmap - Glomap
Gaussian Splatting, point clouds registration,28 repositories
in .cpp Action ( C/C++ )
19 repositories
Instruction Tuning
4 repositories
Interpretability, SAe
Sparse Autoencoders,11 repositories
LLM Inference, Alignment, DPO
plus Preference Tuning + Reward Optimization, high-Throughput, RL, HPO, KV Cache compressions, Reasoning methods, Jailbreaking, TTT n Computation154 repositories
LLM integrations - LAM - GenAI,
+ Action LMs, ecosystems, voice features, TTS, Audio58 repositories
LLM Web Crawler, preproc pipes
10 repositories
LoRA - DoRa (peft)
15 repositories
ML/DL libs
+Thread-based parallelism for data loading65 repositories
NLP -RecSys-clip
essentials, theory, maths base54 repositories
Orchestration of training jobs
on accelerators, TPUs, GPUs on GKE.1 repository
Q-Learning
1 repository
Quant, Blockchain, Decentralised
+ Time-Series modelling,7 repositories
Quantization & Pruning & Sparse
Prune Layers in LLMs, sparsity, Compressions, Vector n Scalar in PyTorch,46 repositories
Rust & Go & TS & db & micro
29 repositories
Scaling, Serving, Benchmarking,
+ Ray.io, BitNet41 repositories
Speculative Decoding n Sampling
7 repositories
SSMs - Toy Models - MoE -Mixtral
33 repositories
Transformers & Attentions
plus Tiny Transformers, mechanisms, optimizers, DiT60 repositories
Triton-NIM-NeMo
11 repositories
World Simulators Models, VGMs
Video Generation models19 repositories
Starred repositories
A simple screen parsing tool towards pure vision based GUI agent
Automate the process of making money online.
Langtrace 🔍 is an open-source, Open Telemetry based end-to-end observability tool for LLM applications, providing real-time tracing, evaluations and metrics for popular LLMs, LLM frameworks, vector…
Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals
Perforator is a cluster-wide continuous profiling tool designed for large data centers
Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜
FPGA based Vision Transformer accelerator (Harvard CS205)
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…
Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS …
A series of technical report on Slow Thinking with LLM
Tune efficiently any LLM model from HuggingFace using distributed training (multiple GPU) and DeepSpeed. Uses Ray AIR to orchestrate the training on multiple AWS GPU instances
Sample code and notebooks for Generative AI on Google Cloud, with Gemini on Vertex AI
This repo aims to record resource of role-playing abilities in LLMs, including dataset, paper, application, etc.
Scale from single vLLM instance to distributed vLLM deployment without changing any application code.
An open source deep research clone. AI Agent that reasons large amounts of web data extracted with Firecrawl
🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library
Training Large Language Model to Reason in a Continuous Latent Space
This repository contains LLM (Large language model) interview question asked in top companies like Google, Nvidia , Meta , Microsoft & fortune 500 companies.
High accuracy RAG for answering questions from scientific documents with citations
Everything you need to build state-of-the-art foundation models, end-to-end.
