Distillative.AI
- 3 followers
- United States of America
- https://www.distillative.ai
- @distillative
- dev@distillative.ai
Popular repositories Loading
-
LightRAG
LightRAG PublicForked from AsherBond/LightRAG
LightRAG: The Lightning Library for LLM Applications.
-
-
-
-
flash-attention
flash-attention PublicForked from AsherBond/flash-attention
Fast and memory-efficient exact attention
Python 1
Repositories
- mcp-typescript-sdk Public Forked from AsherBond/mcp-typescript-sdk
Typescript SDK for Model Context Protocol servers and clients
Distillative-AI/mcp-typescript-sdk’s past year of commit activity - mcp-python-sdk Public Forked from AsherBond/mcp-python-sdk
Distillative.ai Python SDK for Model Context Protocol servers and clients
Distillative-AI/mcp-python-sdk’s past year of commit activity - llm-compressor Public Forked from vllm-project/llm-compressor
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
Distillative-AI/llm-compressor’s past year of commit activity - bionemo-framework Public Forked from NVIDIA/bionemo-framework
BioNeMo Framework: For building and adapting AI models in drug discovery at scale
Distillative-AI/bionemo-framework’s past year of commit activity - NeMo-Agent-Toolkit Public Forked from NVIDIA/NeMo-Agent-Toolkit
The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.
Distillative-AI/NeMo-Agent-Toolkit’s past year of commit activity - earth2studio Public Forked from NVIDIA/earth2studio
Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows.
Distillative-AI/earth2studio’s past year of commit activity - cuEquivariance Public Forked from NVIDIA/cuEquivariance
cuEquivariance is a math library that is a collective of low-level primitives and tensor ops to accelerate widely-used models, like DiffDock, MACE, Allegro and NEQUIP, based on equivariant neural networks. Also includes kernels for accelerated structure prediction.
Distillative-AI/cuEquivariance’s past year of commit activity - Model-Optimizer Public Forked from NVIDIA/Model-Optimizer
A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
Distillative-AI/Model-Optimizer’s past year of commit activity - OSMO Public Forked from ElasticProvisioner/OSMO
The developer-first platform for scaling complex Physical AI workloads across heterogeneous compute—unifying training GPUs, simulation clusters, and edge devices in a simple YAML
Distillative-AI/OSMO’s past year of commit activity
Top languages
Loading…
Most used topics
Loading…