antirez Releases ds4: Local Inference Engine for DeepSeek Across Metal, CUDA, and ROCm
antirez · github · 2026-08-02
ds4 is an open-source local inference engine developed by renowned programmer and Redis creator antirez, specifically tailored for DeepSeek 4 (Flash and PRO versions).
- Hardware Support: Cross-platform support for Apple Metal (M-series chips), NVIDIA CUDA, and AMD ROCm, covering mainstream desktop and edge GPU ecosystems.
- Language: Written in C for maximum performance and efficiency.
- Popularity: Has already garnered nearly 20k stars on GitHub.
More from Infra
- Valtz v0.1.0.11 adds FLUX.3 support, local image gen up to 4K on Mac — TgoAI · 2026-10-16
- Baidu open-sources FlashMask: up to 1.55x faster than FlashAttention-4 for long-context training — BaiduResearch · 2026-10-16
- GYRO quant of Qwen3.8-Flash-Next tested: near Q3 quality at much smaller size — PlasticRevenue4601 · 2026-10-16
- RL train-sample systems are frontier AI's hardest infra problem — and a trade secret — brianryhuang · 2026-10-16
- Local tuning of GLM-5.3-Flash on 2×GB10 lifts decode from 49 to 58 tok/s — EAccelerate_42 · 2026-10-16
- 3x DGX Spark cluster runs GLM-5.3-Flash locally behind a proxy, 1.75M tokens/day at 119W — Teknium · 2026-10-16