Pinned Repositories
Automatic-Differentiation-Custom
Autodiff from the ground up.
candle-lora
Low rank adaptation (LoRA) for Candle.
candle-lora-macro
Macros for candle-lora.
candle-sampling
Sampling techniques for Candle.
candle-vllm
Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.
mistral.rs
Blazingly fast LLM inference.
PerceiverIO-Classifier
A classifier based on PerceiverIO
The-Neuron
An autonomous robot, powered by AI.
trc
A faster Arc.
xlora
X-LoRA: Mixture of LoRA Experts
EricLBuehler's Repositories
EricLBuehler/mistral.rs
Blazingly fast LLM inference.
EricLBuehler/candle-vllm
Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.
EricLBuehler/candle-lora
Low rank adaptation (LoRA) for Candle.
EricLBuehler/xlora
X-LoRA: Mixture of LoRA Experts
EricLBuehler/trc
A faster Arc.
EricLBuehler/candle-sampling
Sampling techniques for Candle.
EricLBuehler/candle-lora-macro
Macros for candle-lora.
EricLBuehler/candle_llm_dataset
A LLM-specific dataset for Candle.
EricLBuehler/candle
Minimalist ML framework for Rust
EricLBuehler/once_arc
Initilize and allocate once, deallocate never.
EricLBuehler/simd_matmul
O(n^2) matmul with SIMD.
EricLBuehler/candle-cublaslt
EricLBuehler/flexrc
Fast, flexible, and safe reference counted type.
EricLBuehler/merlin_rust
Make your code fly.
EricLBuehler/range-checked
Range checked types leveraging Rust's type system.
EricLBuehler/candle-ext
An extension library to Candle that provides PyTorch functions not currently available in Candle
EricLBuehler/candle-layer-norm
EricLBuehler/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
EricLBuehler/EricLBuehler
EricLBuehler/candle-paged-attention
EricLBuehler/candle-rotary
EricLBuehler/cudarc
Safe rust wrapper around CUDA toolkit
EricLBuehler/docs
EricLBuehler/dora
DORA (Dataflow-Oriented Robotic Application) is middleware designed to streamline and simplify the creation of AI-based robotic applications. It offers low latency, composable, and distributed dataflow capabilities. Applications are modeled as directed graphs, also referred to as pipelines.
EricLBuehler/llama_index
LlamaIndex is a data framework for your LLM applications
EricLBuehler/mirage
A multi-level tensor algebra superoptimizer
EricLBuehler/ratchet
A cross-platform browser ML framework.
EricLBuehler/tch-rs
Rust bindings for the C++ api of PyTorch.
EricLBuehler/triomphe
Fork of std::sync::Arc with lots of utilities useful for FFI
EricLBuehler/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs