- Published on
DeepSeek open-sourced its Apache 2.0 production inference engine DeepInfer alongside its 763B Flash model—minus its distributed KV-cache and load balancer.
Inference
All Posts
- ai (13)
- devops (12)
- 5w1h (12)
- aws (8)
- open-source (8)
- productivity (5)
- cloud-native (5)
- llm (5)
- benchmark (5)
- s3 (4)
- efficiency (3)
- security (3)
- claude (3)
- anthropic (3)
- readable (2)
- reusable (2)
- refactorable (2)
- terraform (2)
- kubernetes (2)
- eks (2)
- engineering (2)
- automation (2)
- privacy (2)
- javascript (2)
- self-hosted (2)
- cloud (2)
- agents (2)
- ai-agents (2)
- tet (2)
- celebration (2)
- life (2)
- tools (2)
- programming (2)
- deepseek (2)
- coding-agents (2)
- chatgpt (2)
- frontend (2)
- 2024 (1)
- 2026 (1)
- api (1)
- swagger (1)
- unit-test (1)
- versioning (1)
- exception (1)
- dotnet (1)
- net (1)
- csharp (1)
- c (1)
- clean-code (1)
- version (1)
- manager (1)
- tfenv (1)
- multiple-version (1)
- elastic (1)
- service (1)
- latency (1)
- metrics (1)
- p90 (1)
- p95 (1)
- p99 (1)
- average (1)
- percentile (1)
- performance (1)
- monitoring (1)
- system (1)
- response (1)
- time (1)
- user (1)
- experience (1)
- tail (1)
- sla (1)
- optimize (1)
- t-shaped (1)
- tshaped (1)
- generalist (1)
- specialist (1)
- skill (1)
- engineer (1)
- agility (1)
- career-development (1)
- professional-growth (1)
- interdisciplinary-learning (1)
- engineering-best-practices (1)
- collaboration (1)
- adaptability (1)
- innovation (1)
- specialist-vs-generalist (1)
- workplace-skills (1)
- agile-teams (1)
- team-collaboration (1)
- continuous-learning (1)
- growth-mindset (1)
- skill-development (1)
- cross-functional-teams (1)
- modern-workforce (1)
- career-success (1)
- hybrid-skills (1)
- personal-growth (1)
- kanthor (1)
- can-tho (1)
- cần-thơ (1)
- trip (1)
- fruit (1)
- funny (1)
- n8n (1)
- zapier (1)
- make (1)
- workflow (1)
- tool (1)
- platform (1)
- comparison (1)
- flexibility (1)
- extensibility (1)
- integration (1)
- data (1)
- control (1)
- webhook (1)
- error (1)
- handling (1)
- visual (1)
- era (1)
- revolution (1)
- agentic (1)
- agentic-ai (1)
- autonomy (1)
- intelligence (1)
- blog (1)
- domain (1)
- migration (1)
- github-pages (1)
- nextjs (1)
- nginx (1)
- primax (1)
- milestone (1)
- announcement (1)
- lunar-new-year (1)
- vietnam (1)
- year-of-the-horse (1)
- personal (1)
- reflection (1)
- new-year (1)
- humor (1)
- disaster-recovery (1)
- women (1)
- claude-code (1)
- markdown (1)
- web-scraping (1)
- ecs (1)
- containers (1)
- firefox (1)
- mozilla (1)
- browsers (1)
- enterprise (1)
- google (1)
- gemini (1)
- typescript (1)
- deno (1)
- cloudflare (1)
- nodejs (1)
- typography (1)
- fonts (1)
- devtools (1)
- health (1)
- medicine (1)
- cancer (1)
- self-advocacy (1)
- python (1)
- rust (1)
- polars (1)
- data-engineering (1)
- mistral (1)
- cybersecurity (1)
- apple (1)
- apple-homeview (1)
- smart-home (1)
- siri (1)
- apple-intelligence (1)
- eu-dma (1)
- dario-amodei (1)
- ai-safety (1)
- regulation (1)
- frontier-ai (1)
- openai (1)
- gpt-6 (1)
- intelligent-ui (1)
- generative-ui (1)
- margaret-hamilton (1)
- apollo-11 (1)
- mit (1)
- software-engineering (1)
- computing-history (1)
- obituary (1)
- meta-ai (1)
- muse-wonder (1)
- active-memory (1)
- open-weights (1)
- sakana-ai (1)
- uc-berkeley (1)
- mass (1)
- multi-agent (1)
- self-improvement (1)
- swe-bench (1)
- z-ai (1)
- glm-legal (1)
- legal-ai (1)
- harvey-lab (1)
- benchmarks (1)
- git (1)
- version-control (1)
- monorepo (1)
- web (1)
- indie-dev (1)
- wholesome (1)
- fastapi (1)
- hetzner (1)
- cryptography (1)
- nist (1)
- vllm (1)
- inference (1)
- gpu (1)
- meta (1)
- moe (1)
- opencode (1)
- tesla (1)
- ev (1)
- hardware (1)
- automotive (1)
- hack (1)
- technology (1)
- tips (1)
- reactjs (1)
- webapp (1)
- cdn (1)
- cloudfront (1)
- oh-my-zsh (1)
- zsh (1)
- plugins (1)