Automated Enterprise Inference Stack & Research Lab
AI
Joined May 2023
- Tweets125
- Following340
- Followers450
- Likes274
Pinned Tweet
TheStage AI Platform is now open to everyone.
Automatically accelerate your models and download them to run in the cloud or on smartphones.
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 👇
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: docs.thestage.ai/tutorials/s…
W4A8 Metal kernels for @Apple M5. Run diffusion pipelines up to 3x faster locally on MacBook.
Github: github.com/TheStageAI/qlip-m…
Blogpost: app.thestage.ai/blog/qlip-ml…
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: app.thestage.ai/blog/ComfyUI…
Use ComfyUI nodes from our Github repo: github.com/TheStageAI/ComfyU…
Video is generated by Minimax H3.
The best power consumption for inference on smartphones!
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: app.thestage.ai/blog/Apple-S…
Github: github.com/TheStageAI/AppleS…
Get early access to on-device SDK: github.com/TheStageAI/AppleS…
Lowest power consumption, fast inference, real-time LLMs, ASR, TTS.
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: app.thestage.ai/blog/Apple-S…
Github: github.com/TheStageAI/AppleS…
The best quality open-source GGUF checkpoints for @GoogleDeepMind Gemma4 and @Alibaba_Qwen 3.5
Native @ollama and @lmstudio support.
Github: github.com/TheStageAI/edge-l…
We are releasing accelerated @ComfyUI nodes for multiple diffusion models!
Run Flux, Z-Image, Qwen-Image, LTX 2.3, and Wan 2.2 with NVFP4 quantization and dynamic LoRA switching.
Use the nodes in production: github.com/TheStageAI/ComfyU…
Learn how ComfyUI-Qlip delivers up to 3.6× faster inference with runtime LoRA switching: app.thestage.ai/blog/ComfyUI…
8x compression for @Alibaba_Wan from TheStage AI team!
We have represented low noise expert as high noise expert + LORA and then compressed model with NVFP4.
Now 640x640 video with 20 steps accelerated 72.5s -> 27.8s on @nvidia RTX 5090.
Read our blog: app.thestage.ai/blog/-Wan-2.…
TheStage AI retweeted
240ms TTFA, 2x real-time for @Alibaba_Qwen TTS 0.6B model running on iPhone 16e NPU.
Soon in @TheStageAI SDK: github.com/TheStageAI/AppleS…
TheStage AI retweeted
260 tok/s for @liquidai LFM2.5-230m running with @TheStageAI SDK on iPhone 16e NPU