ved1beta/ved1beta
Config files for my GitHub profile.
Hi, I'm Ved! 🗣 , AI Infra | LLM Inference | Systems Performance
Repositories
ved1beta/CUDA_MLpapers
ML papers Implementation
ved1beta/mlx
MLX: An array framework for Apple silicon
ved1beta/nanospec
inference engine with speculative decoding.
ved1beta/axolotl
Go ahead and axolotl questions
ved1beta/ml-cross-entropy
ved1beta/speculators
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
ved1beta/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
ved1beta/hailmary
kimi4all
ved1beta/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
ved1beta/hatchery-core
ved1beta/sglang-jax
JAX backend for SGL
ved1beta/jax-sanghatan
writingjaxtobekool
ved1beta/v.o_clone
wrote v0.dev backend and inspired by bolt.new in TS
ved1beta/trl
Train transformer language models with reinforcement learning.
ved1beta/tvm-ffi
Open ABI and FFI for Machine Learning Systems
ved1beta/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
ved1beta/dlpack
common in-memory tensor structure
ved1beta/Cuda_writer
Distributed training
ved1beta/flashinfer
FlashInfer: Kernel Library for LLM Serving
ved1beta/Liger-Kernel
Efficient Triton Kernels for LLM Training
ved1beta/kernels
Build compute kernels and load them from the Hub.
ved1beta/GPU-sanghathan
Small scale distributed training of sequential deep learning models, built on Numpy and MPI.
ved1beta/Quanta
"Efficient and scalable solutions for PyTorch, enabling large language model quantization with k-bit precision for enhanced accessibility.
ved1beta/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
ved1beta/llama-stack
Composable building blocks to build Llama Apps
ved1beta/arc
ARC Relay — WebSocket relay server for agent remote control by Axolotl AI
ved1beta/vhidushak
E2E pipeline 4 inference
ved1beta/100Days
ved1beta/tt-mlir
Tenstorrent MLIR compiler