Redis Author Optimizes DeepSeek V4 to 45 t/s
Redis author antirez demonstrated the DwarfStar inference engine, optimizing DeepSeek V4 PRO to 45 t/s via Q2 quantization and dynamic expert routing. The system adaptively migrates experts between VRAM and RAM based on usage.
2026-08-17 ~ 2026-08-17 · 3 related posts
- Episode 1: Redis Author Optimizes DeepSeek V4 to 45 t/s(2026-08-17, 3 posts)
- Episode 2: antirez Tunes DwarfStar to 170 t/s Generation on Station(2026-08-17, 2 posts)
- Episode 3: DeepSeek v4 local deployment hits 3000 t/s prefill on DGX Station(2026-08-18, 2 posts)
- DeepSeek v4 PRO Q2 hits 45 t/s with VRAM/RAM split on DGX Station — antirez · 2026-08-17
- antirez's DwarfStar: adaptive VRAM/RAM expert placement runs DeepSeek V4 at 45 t/s — antirez · 2026-08-17
- Dynamic Expert Migration: Adaptive Optimization from VRAM to RAM — antirez · 2026-08-17