DeepSeek open-sources its production inference engine for V4.1 Flash, runs on Blackwell and Ascend
altryne · x · 2026-10-25
DeepSeek has open-sourced the inference engine it actually uses to serve V4.1 Flash in production, under Apache 2.0, with support for both NVIDIA Blackwell and Huawei Ascend hardware.
Key points:
- The pitch: serve more users on the same hardware and keep the margin — reactions call it a "broke the internet" moment
- Host altryne discusses DeepInfer and what's still missing in the inference stack with Yam Peleg and ldjconfirmed
- Dual support for US and Chinese chips is notable against the current compute-geopolitics backdrop
Related event: DeepSeek Open-Sources DeepInfer, the Inference Engine Behind V4.1 Flash(4 posts)→
More from Infra
- 305M-Parameter Sparse MoE Runs Computer-Use Agent Fully Offline on a MacBook Air — lmoroney · 2026-10-25
- SGLang reruns DeepInfer on matching hardware, matches or beats its prefill performance — hsu_byron · 2026-10-25
- Anthropic in talks for $45B compute deal with Nscale for 460MW of Vera Rubin capacity — Beth_Kindig · 2026-10-25
- DIY GPU cluster war stories: PCIe retimers can literally catch fire — giffmana · 2026-10-25
- GPT-6.1 Sol beats Opus 5.5 on cost-performance balance, argues dev who caught Opus in logic traps — haider1 · 2026-10-25
- Abliterated DeepSeek V4.1 Flash GGUF hits Hugging Face trending — orcarouter · 2026-10-25