← Latest products

DeepSeek-V4 Latent Reasoning

moving "thinking" into latent space. DeepSeek-V4-Flash-0731-Latent-Reasoning. A self-contained model that does thinking in latent space, NVFP4-quantized, with a production vllm form for….

Visit blog.n.ichol.aiexternal site

Reactions (1)

Similar products

by description similarity

  1. Deep Research

    github.com

    Open-Source Customizable Reasoning Framework for Devs

    Hacker News7 pts

  2. KTransformers:671B DeepSeek-R1 on a Single Machine-286 tokens/s Prefill

    github.com

    A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

    Hacker News20 pts

  3. r1_vlm

    github.com

    Open-Source Framework for Visual Reasoning with GRPO

    Hacker News5 pts

  4. ThinkGPT

    github.com

    a library to prompt GPT to think, memorize and self-refine

    Hacker News48 pts

  5. LLM Inference Calculator

    llm-inference-calculator-delta.vercel.app

    Estimate VRAM, Latency, and Throughput

    Hacker News6 pts