nltpt

Enterprise

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

reach-vb new activity 27 days ago

meta-llama/Llama-3.3-70B-Instruct:Update the "How to use" instructions.

reach-vb updated a model 27 days ago

meta-llama/Llama-3.3-70B-Instruct

vontimitta new activity 27 days ago

meta-llama/Llama-3.3-70B-Instruct-evals:Update license

View all activity

nltpt's activity

Xenova

posted an update about 20 hours ago

Post

1216

First project of 2025: Vision Transformer Explorer

I built a web app to interactively explore the self-attention maps produced by ViTs. This explains what the model is focusing on when making predictions, and provides insights into its inner workings! 🤯

Try it out yourself! 👇
webml-community/attention-visualization

Source code: https://github.com/huggingface/transformers.js-examples/tree/main/attention-visualization

Xenova

posted an update 15 days ago

Post

2552

Introducing Moonshine Web: real-time speech recognition running 100% locally in your browser!
🚀 Faster and more accurate than Whisper
🔒 Privacy-focused (no data leaves your device)
⚡️ WebGPU accelerated (w/ WASM fallback)
🔥 Powered by ONNX Runtime Web and Transformers.js

Demo: webml-community/moonshine-web
Source code: https://github.com/huggingface/transformers.js-examples/tree/main/moonshine-web

5 replies

Narsil

posted an update 21 days ago

Post

1012

Performance leap: TGI v3 is out. Processes 3x more tokens, 13x faster than vLLM on long prompts. Zero config !

3x more tokens.

By reducing our memory footprint, we’re able to ingest many more tokens and more dynamically than before. A single L4 (24GB) can handle 30k tokens on llama 3.1-8B, while vLLM gets barely 10k. A lot of work went into reducing the footprint of the runtime and its effect are best seen on smaller constrained environments.
13x faster

On long prompts (200k+ tokens) conversation replies take 27.5s in vLLM, while it takes only 2s in TGI. How so ? We keep the initial conversation around, so when a new reply comes in, we can answer almost instantly. The overhead of the lookup is ~5us. Thanks @Dani ël de Kok for the beast data structure.
Zero config

That’s it. Remove all the flags your are using and you’re likely to get the best performance. By evaluating the hardware and model, TGI carefully selects automatic values to give best performance. In production, we don’t have any flags anymore in our deployments. We kept all existing flags around, they may come in handy in niche scenarios.

Read more: https://huggingface.co/docs/text-generation-inference/conceptual/chunking

Xenova

posted an update 25 days ago

Post

2950

Introducing TTS WebGPU: The first ever text-to-speech web app built with WebGPU acceleration! 🔥 High-quality and natural speech generation that runs 100% locally in your browser, powered by OuteTTS and Transformers.js. 🤗 Try it out yourself!

Demo: webml-community/text-to-speech-webgpu
Source code: https://github.com/huggingface/transformers.js-examples/tree/main/text-to-speech-webgpu
Model: onnx-community/OuteTTS-0.2-500M (ONNX), OuteAI/OuteTTS-0.2-500M (PyTorch)