Huge update of our Android SDK.
@liquidai LFM3 1.7B up to 540 tps on @Qualcomm Snapdragon NPU.
Reached the theoretical memory bandwidth limit on Qualcomm NPUs. Read blog and try Android SDKπ
We helped @JensenHuang to catch all GPUs using @liquidai LFM2.5-1.2B and our new @Apple NPU friendly speculative decoding.
4x acceleration on average. Blog and Github π
@Qualcomm Android SDK! High-quality TTS, VLM, ASR, and more! Strong NPU support!
Quantised and accelerated with TheStage AI ANNA + MTP.
Read release notes: https://t.co/dkPLtzN5aN
Build real-time on-device multilingual TTS pipeline with TheStage AI Apple SDK.
Export your voice references and ship it with application bundle. In the result you will get dynamically switching language TTS.
Inference support @Alibaba_Qwen tts 0.6b and @neuphonicspeech multilingual nano model.
Read tutorial how to integrate it to your app: https://t.co/YeL5cgmR8W
W4A8 Metal kernels for @Apple M5. Run diffusion pipelines up to 3x faster locally on MacBook.
Github: https://t.co/xRNKFBt96y
Blogpost: https://t.co/eUMwnJclr7
Experimental release to utilize M5 GPU neural accelerator with int8 vector instructions.
Up to 5.6x faster generation for diffusion pipelines with @ComfyUI support! New self-hosting engines!
@MiniMax_AI H3 4x faster, @krea_ai 2 turbo 5.6x faster, @ideogram_ai 1.6x faster, @AlibabaGroup Z-image-turbo 5.1x faster!
We are introducing new nodes for acceleration of your pipelines:
- Auto Sparse Attention
- Progressive generation (upsample feature maps during generation)
- Cache Nodes.
Read our tech report: https://t.co/PCq1Zkr86f
Use ComfyUI nodes from our Github repo: https://t.co/OkkpH3StkQ
Video is generated by Minimax H3.
Want to learn about power consumption, thermal throttling, automated model compression, or why NPU is better than CPU and GPU?
Check out @TheStage AI Apple on-device SDK!
Read our tech report and request access to the SDK for early testing! Up to 6x power consumption reduction comparing to GPU inference.
LLMs, TTS, ASR with real-time streaming support and voice agent orchestration.
Tech report: https://t.co/Pr2bAmXWjO
Github: https://t.co/yVWjvMWiEo