#DeepSeek
318 related articles
Abliterated DeepSeek Inference Providers Grow to Five
Abliterated DeepSeek inference providers have grown to five, sparking Hacker News discussion. This article explains abliteration, why multiple providers emerged, and the practical impact on choice, version consistency, and compliance risk.
DeepSeek Open-Sources DeepInfer: Inference Cost Reduction and the Shifting Landscape of Domestic Chips
DeepSeek open-sources DeepInfer, its internal inference framework compatible with NVIDIA and Ascend 950, achieving structural cost reduction through KV cache compression and PD disaggregation. This article examines its open-source boundaries, impact on the domestic chip landscape, and new hardware expectations like UE8M0 FP8.
Open-Source AI Desktop Pet Coopanion: DeepSeek's Big Fat Fish Moves Into Your Taskbar
Open-source AI desktop pet Coopanion puts 13 models including DeepSeek into your taskbar, with five personalities, versioned local memory, confirmation before actions, and even Plants vs. Zombies. 350+ stars in under four weeks and 20+ derivative projects.
DeepSeek Open-Sources DeepInfer: Inference Costs Slashed and Commercial Licensing Fully Open
DeepSeek open-sources DeepInfer, a permissively licensed inference framework for commercial use. Speculative decoding cuts payback from 10 to 4 months.
DeepSeek Open-Sources DeepInfer: How Opening Up the Inference Framework Shakes Up the AI Ecosystem
DeepSeek open-sources its inference framework DeepInfer, opening up models, code, and the inference stack. This analysis examines the impact on the developer ecosystem, competition with closed-source vendors, and the trend of open-source AI moving from weights to full stack.
DeepSeek Open-Sources Its Inference Framework DeepInfer: The Economics of Inference Services and Industry Impact
DeepSeek open-sources its in-house inference framework DeepInfer, revealing for the first time its cost-revenue model: a 128-GPU cluster earns over $40M annually. This article analyzes KV Cache, Prefill/Decode disaggregation, and other technical optimizations, the impact of open-sourcing on cloud providers and third-party API vendors, and DeepSeek's true intent in building an ecosystem.
DeepSeek 4.1 Flash Hands-On: The Strongest Open-Source Model and DeepInfer's Ambitions
DeepSeek 4.1 Flash hands-on: the strongest open-source model's real performance in video generation, 3D games, and the frog test, plus what DeepInfer's cache hit rate, gross margin, and Huawei chip support mean.
Three Releases in 18 Hours: Strata Runs DeepSeek V4.1 Flash on a 12GB GPU
Strata shipped three releases in 18 hours (0.2.3, 0.2.3.1, 0.2.4), using RAM as VRAM, skipping redundant compute, and speculative decoding to run DeepSeek V4.1 Flash on a 12GB GPU plus 46GB RAM.
DeepSeek Open-Sources Inference Engine: 80% Gross Margin Crushes Silicon Valley, but Copycats Find the Assembly Line Missing
DeepSeek open-sources its inference engine DeepInfer and Rust gateway DeepSeek Recipe, revealing 155T tokens/day at 80% gross margin. A breakdown of causal encoder-decoder architecture, wide expert parallelism, EPLB, dSpark, bounded replay, and Ascend 950 support—plus the three closed-source barriers that remain.
Run Claude Code for Free: DeepSeek V3 & Gemini API Integration Guide
Learn to use a one-click Windows installer to switch Claude Code's backend to DeepSeek V3, Gemini, or free OpenRouter APIs—zero-cost terminal AI coding, with full setup and limitations.
Understanding DeepSeek in 3 Minutes: The Rise from a Quant Hedge Fund to an Open-Source AI Leader
DeepSeek's history in 3 minutes: from High-Flyer Quant's compute build-up to V2's MLA inference cost cuts, V3's $5.576M training bill, R1's open-source global shock, and V4 with a $7B Series A.
Liang Wenfeng's Three Big Bets: Why Did DeepSeek Open-Source Its 82% Gross Margin?
Why did DeepSeek open-source DeepInfer, its 82% gross margin inference framework, and then launch a hundred-billion funding round? An analysis of Liang Wenfeng's three big bets and the open-source strategy.
DeepSeek Open-Sources Inference Engine DeepInfer: All the Cost-Saving Tricks Laid Bare
DeepSeek open-sources inference engine DeepInfer and Recipe. We break down PD disaggregation, KV cache, SWA bounded replay, speculative decoding, and what $38 unit economics really means.
DeepSeek Harness Step-by-Step Installation Guide: Core Principles and Building Automated AI Applications
Based on Bilibili creator Pan Ge's DeepSeek Harness tutorial, this guide covers Node.js installation, npm global directory and cache configuration, environment variables, and the core principles of Harness with Agents.
Liang Wenfeng Open-Sources DeepInfo Inference Framework, Takes On U.S. Ban
DeepSeek open-sources its DeepInfo inference framework after its models, featuring GPU/CPU cross-pipelining, small-model prediction with large-model verification, and full Huawei Ascend and NVIDIA chip support—facing the U.S. federal ban head-on. This article analyzes its significance for AI deployment and open-source strategy.
Building a Theresa-Themed Plugin for DeepSeek Harness by Hand, Open-Sourcing Planned
Bilibili creator develops a "Theresa" theme plugin for DeepSeek Harness with background transparency adjustment, character art upload, and phantom page text customization. Copyright concerns over official materials and fan art delay open-sourcing; GitHub release planned.
DeepSeek Open-Sources Inference Engine DeepInfer: The AI Cost War and the Contest Over National Destiny
DeepSeek open-sources DeepInfer under Apache 2.0, boosting prefill throughput 25x and supporting NVIDIA SM100 and Huawei Ascend 950. A deep dive into its optimizations, open-source strategy, and the AI cost war.
DeepSeek's Open-Source Inference Framework: The Compute Economics Behind $330K Annual Revenue Per GPU
DeepSeek's open-source inference framework reveals a $38/GPU/hour floor price—how the $330K/year per-GPU math works, plus prefill-decode disaggregation and KV cache.
Leaked DeepSeek Internal Chat Screenshot: Open Source Doesn't Mean Giving Away the Whole Empire
Leaked DeepSeek internal chat screenshot goes viral, with netizens joking about what's left after open-sourcing. This article analyzes the difference between open-source models and giving away all assets, explaining why computing clusters, engineering teams, and business channels can't be replicated, and the ecosystem positioning logic behind open source as a business strategy.
DeepSeek Open-Sources Inference Framework Deepinflow: The AI Price War Moves into the Back Kitchen
DeepSeek open-sources its internal inference framework Deepinflow, revealing optimization experience in high-performance operators, parallelism strategies, and speculative decoding—challenging the high-priced API model of OpenAI and other giants by open-sourcing deployment efficiency to disrupt AI pricing logic and push large model inference from luxury good to public infrastructure.