Chinese search giant Baidu unveiled two new AI accelerators this week amid a national push to end reliance on Western chips.

Baidu was an early adopter of generative AI technologies, developing models like its ERNIE family. Like many Western cloud providers, including Amazon and Google, Baidu has been designing custom accelerators for years.

According to the South China Morning Post, the search provider's latest generation of chips aims to [1]drive down inference costs and support larger, more complex architectures.

[2]

The company plans to release a new inference-optimized chip, the M100, next year. It was developed by its Kunlunxin chip unit to better serve the next generation of mixture-of-experts (MoE) models.

[3]

[4]

As we've recently [5]explored , MoE architectures present specific challenges for inference at scale, particularly as models grow beyond a single accelerator or server. In many cases, interconnect bandwidth and latency become a bottleneck, inhibiting performance.

It appears Baidu aims to sidestep this particular issue by building larger compute domains, similar to what AMD and Nvidia are doing with their own [6]rack-scale architectures. Baidu plans to offer the chips in a clustered configuration called the Tianchi256 beginning in early 2026. As the name suggests, the configuration will feature 256 M100 accelerators.

[7]

Baidu will reportedly expand the system to an even larger compute domain with the launch of the Tianchi512 in late 2026, which will double the system's inference capacity.

Alongside inference serving, Baidu is also working on a more powerful training-optimized chip called the M300, which will make its debut in 2027. The chip aims to support the training of multi-trillion-parameter models, which have become increasingly common over the past year, with Moonshot AI's Kimi K2 being just one example.

Alongside the new silicon, Baidu [8]announced ERNIE 5.0, its latest foundation model, capable of working with text, images, audio, and videos.

[9]

Baidu's latest hardware underscores a strategic shift by the Chinese away from Nvidia accelerators. Officials in Beijing have reportedly pressured tech titans to ditch Western suppliers in favor of domestic alternatives.

[10]HPE details Vera Rubin blades for next-gen Cray supercomputers

[11]Britain's first small modular reactors to be built in Wales

[12]Blackwell a no-sell in China as trade deal fails to materialize

[13]White House says China to lift rare earth export bans, stop probes into US tech companies

Last week, Nvidia CEO Jensen Huang [14]admitted that efforts to sell its Blackwell accelerators in China had stalled and that there were currently no "active discussions."

The sea change has bolstered efforts by Huawei and other Chinese chipmakers, including Biren, Cambricon Technologies, and MetaX, to bring home-grown GPUs to market.

Earlier this year, we [15]looked at Huawei's new CloudMatrix 384 rack machines. While nowhere near as efficient as Nvidia's Blackwell family, they make up for it with sheer scale. ®

Get our [16]Tech Resources



[1] https://www.scmp.com/tech/big-tech/article/3332596/baidu-unveils-ai-chips-boost-chinas-self-sufficiency-drive

[2] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_software/aiml&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=2&c=2aRZjBankjdKtgQOODnQ5BwAAAUA&t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0

[3] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_software/aiml&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=4&c=44aRZjBankjdKtgQOODnQ5BwAAAUA&t=ct%3Dns%26unitnum%3D4%26raptor%3Dfalcon%26pos%3Dmid%26test%3D0

[4] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_software/aiml&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=3&c=33aRZjBankjdKtgQOODnQ5BwAAAUA&t=ct%3Dns%26unitnum%3D3%26raptor%3Deagle%26pos%3Dmid%26test%3D0

[5] https://www.theregister.com/2025/11/05/perplexity_1t_parameter_models_aws_efa/

[6] https://www.theregister.com/2025/06/25/rack_scale_networking/

[7] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_software/aiml&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=4&c=44aRZjBankjdKtgQOODnQ5BwAAAUA&t=ct%3Dns%26unitnum%3D4%26raptor%3Dfalcon%26pos%3Dmid%26test%3D0

[8] https://www.prnewswire.com/news-releases/baidu-unveils-ernie-5-0-and-a-series-of-ai-applications-at-baidu-world-2025--ramps-up-global-push-302614531.html

[9] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_software/aiml&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=3&c=33aRZjBankjdKtgQOODnQ5BwAAAUA&t=ct%3Dns%26unitnum%3D3%26raptor%3Deagle%26pos%3Dmid%26test%3D0

[10] https://www.theregister.com/2025/11/13/hpe_details_vera_rubin_blades/

[11] https://www.theregister.com/2025/11/13/anglesey_smr/

[12] https://www.theregister.com/2025/11/07/china_nvidia_blackwell/

[13] https://www.theregister.com/2025/11/03/asia_tech_news_roundup/

[14] https://www.theregister.com/2025/11/07/china_nvidia_blackwell/

[15] https://www.theregister.com/2025/07/29/huawei_rackscale_boogeyman/

[16] https://whitepapers.theregister.com/