DeepSeek Reportedly Developing Own AI Inference Chip
智东西 · wechat · 2026-07-07
Reuters reports, citing three sources, that DeepSeek is developing its own AI chip tailored for inference to reduce reliance on Nvidia and Huawei. The project started about a year ago and remains in early stages. DeepSeek is currently engaging with chip design, wafer foundry, and memory vendors, while quietly expanding its chip design engineering team. DeepSeek currently uses both Nvidia and Huawei chips; its V4 model released in April is adapted for Ascend chips, and Huawei stated Ascend was involved in training part of V4-Flash.
As the cost pressure for large models shifts from training to inference, developing proprietary inference chips is becoming a consensus among top AI labs: OpenAI has partnered with Broadcom to launch its first inference chip, Jalapeno, and Anthropic is reportedly evaluating its own chip options. Meanwhile, DeepSeek emailed API customers that the official V4 release is planned for mid-July, with the API adopting peak and off-peak pricing.
More from Companies & People
- Anthropic Insiders: Not Everyone at the Lab Believes in High p(doom) — anpaure · 2026-09-11
- Lumara AI Film Festival Comes to NYC Oct 26, Top AI Filmmakers to Compete — 0xAllen_ · 2026-09-11
- X drama: Anthropic researchers accused of spying on academic customers and racing them to results — basedjensen · 2026-09-11
- Investor argues Palantir-Nvidia partnership should slash Anthropic's IPO valuation — pdamodaran · 2026-09-11
- a16z podcast: why 2-3 person startups are absent from policy debates — a16z Podcast · 2026-09-11
- PyTorch Day Korea 2026 launches first offline conf, CFP closes Sept 13 — PyTorch · 2026-09-11