DeepSeek

Expert Parallelism Load Balancer
Updated 2026-11-09 16:19:34 +00:00
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Updated 2026-11-09 16:19:26 +00:00
A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.
Updated 2026-11-09 16:19:25 +00:00
Towards a More Autonomous Agent System
Updated 2026-11-09 16:19:24 +00:00
An internal component used by DeepSeek Harness
Updated 2026-11-09 16:19:16 +00:00
An internal component used by DeepSeek Harness
Updated 2026-11-09 16:19:16 +00:00
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
Updated 2026-11-09 16:19:13 +00:00
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
Updated 2026-11-09 16:19:07 +00:00
DeepSelect: TopK kernels for DeepSeek Sparse Attention (DSA) and Samplers
Updated 2026-11-09 16:19:06 +00:00
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
Updated 2026-11-09 16:19:04 +00:00
Updated 2026-11-09 16:18:57 +00:00
DeepSeek-VL: Towards Real-World Vision-Language Understanding
Updated 2026-11-09 16:18:57 +00:00
Updated 2026-11-09 16:18:54 +00:00
Updated 2026-11-09 16:18:47 +00:00
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Updated 2026-11-09 16:18:47 +00:00