deepseek-ai

DeepInfer

Python 0 0

DeepInfer: High-performance, large-scale inference framework for DeepSeek models

Updated 2026-11-03 07:31:40 +00:00

TileKernels

Python 0 0

A kernel library written in tilelang

Updated 2026-10-14 05:49:06 +00:00

DeepSpec

Python 0 0

DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

Updated 2026-07-09 04:37:14 +00:00

DeepSeek-OCR-2

Python 0 0

Visual Causal Flow

Updated 2026-02-03 00:34:17 +00:00

DualPipe

Python 0 0

A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.

Updated 2026-01-14 06:34:58 +00:00

Engram

Python 0 0

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Updated 2026-01-14 01:13:02 +00:00

DeepSeek-Math-V2

Python 0 0

Updated 2025-12-01 07:01:35 +00:00

LPLB

Python 0 0

An early research stage expert-parallel load balancer for MoE models based on linear programming.

Updated 2025-11-19 07:19:47 +00:00

DeepSeek-V3.2-Exp

Python 0 0

Updated 2025-11-18 02:49:02 +00:00

DeepSeek-Coder

Python 0 0

DeepSeek Coder: Let the Code Write Itself

Updated 2025-11-11 06:44:55 +00:00

DeepSeek-V3

Python 0 0

Updated 2025-08-28 03:24:26 +00:00

ESFT

Python 0 0

Expert Specialized Fine-Tuning

Updated 2025-05-22 07:47:10 +00:00

DreamCraft3D

Python 0 0

[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

3d-creation 3d-generation aigc diffusion-models generative-model image-to-3d

Updated 2025-04-22 11:09:39 +00:00

EPLB

Python 0 0

Expert Parallelism Load Balancer

Updated 2025-03-24 09:17:10 +00:00

smallpond

Python 0 0

A lightweight data processing framework built on DuckDB and 3FS.

data-processing duckdb

Updated 2025-03-05 18:23:52 +00:00