Loading video...

Video Failed to Load

Go Home

Releasing kyutai pocket TTS inference in webgpu today — it’s open-source, here’s a demo from my phone It took a while and a bunch of code to implement streaming inference from scratch!

ekzhang1's profile picture

Eric Zhang

21,504 subscribers

22,085 views • 6 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Kyutai Speech-To-Text is now open-source! It’s streaming, supports batched inference, and runs blazingly fast: perfect for interactive applications. Check out the details here:
0:53

Kyutai Speech-To-Text is now open-source! It’s streaming, supports batched inference, and runs blazingly fast: perfect for interactive applications. Check out the details here:

kyutai

66,503 views • 1 year ago

Releasing moondream-zig! It is a fast, implementation of moondream2 inference on the CPU written from-scratch in Zig :) moondream-zig provides 1.5-2x faster inference compared to huggingface on the same device. moondream vik
1:21

Releasing moondream-zig! It is a fast, implementation of moondream2 inference on the CPU written from-scratch in Zig :) moondream-zig provides 1.5-2x faster inference compared to huggingface on the same device. moondream vik

snow

29,245 views • 1 year ago

BOOM! Starting today you can use open source frontier LLMs in Visual Studio Code with HF Inference Providers! 🔥 Use your inference credits on SoTA llms like GLM 4.5, Qwen3 Coder, DeepSeek 3.1 and more All of it packaged in one simple extension - try it out today 🤗
1:52

BOOM! Starting today you can use open source frontier LLMs in Visual Studio Code with HF Inference Providers! 🔥 Use your inference credits on SoTA llms like GLM 4.5, Qwen3 Coder, DeepSeek 3.1 and more All of it packaged in one simple extension - try it out today 🤗

Vaibhav (VB) Srivastav

41,201 views • 11 months ago

What is AI inference engineering, why is it such an in-demand skill, and how do you break into the field? With author of Inference Engineering Philip Kiely and head of training at Baseten Charlie O'Neill 0:00: What is inference? 2:47: History of inference 4:59: Downstream effects of AI research on inference 13:54: What you'll learn from Inference Engineering 16:14: Advice for engineers transitioning into AI 19:00: Open source models driving inference growth 20:55: Specialization vs. frontier closed models 23:51: "Big Token" and the importance of open source AI 27:18: Where to get Inference Engineering
27:58

What is AI inference engineering, why is it such an in-demand skill, and how do you break into the field? With author of Inference Engineering Philip Kiely and head of training at Baseten Charlie O'Neill 0:00: What is inference? 2:47: History of inference 4:59: Downstream effects of AI research on inference 13:54: What you'll learn from Inference Engineering 16:14: Advice for engineers transitioning into AI 19:00: Open source models driving inference growth 20:55: Specialization vs. frontier closed models 23:51: "Big Token" and the importance of open source AI 27:18: Where to get Inference Engineering

Madison Kanna

119,268 views • 4 months ago

releasing v0.1 of Papercode today! - a fun platform for getting back to implementing papers from scratch - you can implement papers from scratch using leetcode style interfaces :D - auth, good storage coming soon - this is a barebones structure at this point, so please report any bugs in my dms please do share and use it well :) link in replies
0:26

releasing v0.1 of Papercode today! - a fun platform for getting back to implementing papers from scratch - you can implement papers from scratch using leetcode style interfaces :D - auth, good storage coming soon - this is a barebones structure at this point, so please report any bugs in my dms please do share and use it well :) link in replies

neural nets.

17,535 views • 8 months ago

Before Fable 5 was shut down, it pushed Gemma 4 to 255 tok/s on WebGPU. Some didn't believe it was real. Today we're releasing the demo and kernels it wrote for you to see yourself. Run it locally in your browser. Agentic kernel optimization is the future of on-device inference
0:57

Before Fable 5 was shut down, it pushed Gemma 4 to 255 tok/s on WebGPU. Some didn't believe it was real. Today we're releasing the demo and kernels it wrote for you to see yourself. Run it locally in your browser. Agentic kernel optimization is the future of on-device inference

Xenova

483,082 views • 1 month ago

Introducing Open TTS Tracker! 🗣️ *sound on* A one-stop shop to track all open access/ source TTS models! Ranging from XTTS to Pheme, OpenVoice to VITS, and more... ⚡ For each model, we compile: 1. Souce-code 2. Checkpoints 3. License 4. Fine-tuning code 5. Languages supported 6. Paper 7. Demo Help us make it more complete! Let's 2024 the year of open TTS models! ❤️
1:27

Introducing Open TTS Tracker! 🗣️ *sound on* A one-stop shop to track all open access/ source TTS models! Ranging from XTTS to Pheme, OpenVoice to VITS, and more... ⚡ For each model, we compile: 1. Souce-code 2. Checkpoints 3. License 4. Fine-tuning code 5. Languages supported 6. Paper 7. Demo Help us make it more complete! Let's 2024 the year of open TTS models! ❤️

Vaibhav (VB) Srivastav

68,037 views • 2 years ago

AI inference is already live on UOMI Router. Access frontier open-source models through a decentralized inference network with: • Low-cost inference • OpenAI-compatible APIs • Verifiable compute • On-chain settlement Start building: And if you have idle GPUs, there's now a second way to participate. The UOMI Provider whitelist is officially open. Instead of letting your hardware sit unused, you can contribute GPU power to the UOMI Inference Network and earn from real AI demand. Join the Provider whitelist:
0:34

AI inference is already live on UOMI Router. Access frontier open-source models through a decentralized inference network with: • Low-cost inference • OpenAI-compatible APIs • Verifiable compute • On-chain settlement Start building: And if you have idle GPUs, there's now a second way to participate. The UOMI Provider whitelist is officially open. Instead of letting your hardware sit unused, you can contribute GPU power to the UOMI Inference Network and earn from real AI demand. Join the Provider whitelist:

Uomi

18,923 views • 1 month ago

⚡️Today marks a big milestone for Nebius. We’re launching Nebius Token Factory, the evolution of Nebius AI Studio, built to make open-source AI production-grade. Token Factory transforms raw open models into governed, scalable systems with dedicated inference, sub-second latency, 99.9% uptime and zero-retention compliance. It’s where inference, post-training and governance converge, turning raw compute into reliable intelligence. Run AI inference at scale:
0:53

⚡️Today marks a big milestone for Nebius. We’re launching Nebius Token Factory, the evolution of Nebius AI Studio, built to make open-source AI production-grade. Token Factory transforms raw open models into governed, scalable systems with dedicated inference, sub-second latency, 99.9% uptime and zero-retention compliance. It’s where inference, post-training and governance converge, turning raw compute into reliable intelligence. Run AI inference at scale:

Nebius Token Factory

260,215 views • 9 months ago

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 + source code below 👇
0:32

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 + source code below 👇

Xenova

19,666 views • 1 year ago

Open source like DeepSeek doesn’t shrink markets. It grows them. Faster, cheaper training means rising inference demand and a new era of AI hardware.
0:47

Open source like DeepSeek doesn’t shrink markets. It grows them. Faster, cheaper training means rising inference demand and a new era of AI hardware.

The Linux Foundation

32,930 views • 1 year ago

Yesterday: iPad demo Today: iPhone demo Same headless Mac mini setup, but now you can manage AI agents from your pocket. Here’s a quick demo of how I remotely connect from anywhere with my iPhone to monitor what’s happening, and take over when needed
1:18

Yesterday: iPad demo Today: iPhone demo Same headless Mac mini setup, but now you can manage AI agents from your pocket. Here’s a quick demo of how I remotely connect from anywhere with my iPhone to monitor what’s happening, and take over when needed

Matt Ronge

4,707,374 views • 4 months ago

Today we announced a $150M seed round in Inferact, a new startup led by the maintainers of the vLLM project. Inferact will support the vLLM open source project through dedicated financial and developer resources and build what they see as the next generation commercial inference engine. Cofounders Simon Mo and Woosuk Kwon joined a16z GP Matt Bornstein for a conversation on how vLLM came to be, what they’ve learned from building it, and what they’re now doing at Inferact. They cover how vLLM began as a side project, why open source is essential to the world’s AI infrastructure, why inference is getting harder, and more. 00:00 Introduction 11:41 Community and collaboration in vLLM 19:19 Understanding inference engines 24:27 Cluster scale and GPU deployment 31:19 Belief in open source AI 35:45 Founding Inferact 40:00 The future of Inference at scale Simon Mo Woosuk Kwon Matt Bornstein
44:14

Today we announced a $150M seed round in Inferact, a new startup led by the maintainers of the vLLM project. Inferact will support the vLLM open source project through dedicated financial and developer resources and build what they see as the next generation commercial inference engine. Cofounders Simon Mo and Woosuk Kwon joined a16z GP Matt Bornstein for a conversation on how vLLM came to be, what they’ve learned from building it, and what they’re now doing at Inferact. They cover how vLLM began as a side project, why open source is essential to the world’s AI infrastructure, why inference is getting harder, and more. 00:00 Introduction 11:41 Community and collaboration in vLLM 19:19 Understanding inference engines 24:27 Cluster scale and GPU deployment 31:19 Belief in open source AI 35:45 Founding Inferact 40:00 The future of Inference at scale Simon Mo Woosuk Kwon Matt Bornstein

a16z

87,993 views • 6 months ago

New course: Efficient Inference with SGLang: Text and Image Generation, built in partnership with LMSys LMSYS Org and RadixArk RadixArk, and taught by Richard Chen Richard Chen, a Member of Technical Staff at RadixArk. Running LLMs in production is expensive, and much of that cost comes from redundant computation. This short course teaches you to eliminate that waste using SGLang, an open-source inference framework that caches computation already done and reuses it across future requests. When ten users share the same system prompt, SGLang processes it once, not ten times. The speedups compound quickly, especially when there's a lot of shared context across requests. Skills you'll gain: - Implement a KV cache from scratch to eliminate redundant computation within a single request - Scale caching across users and requests with RadixAttention, so shared context is only processed once - Accelerate image generation with diffusion models using SGLang's caching and multi-GPU parallelism Join and learn to make LLM inference faster and more cost-efficient at scale!
1:51

New course: Efficient Inference with SGLang: Text and Image Generation, built in partnership with LMSys LMSYS Org and RadixArk RadixArk, and taught by Richard Chen Richard Chen, a Member of Technical Staff at RadixArk. Running LLMs in production is expensive, and much of that cost comes from redundant computation. This short course teaches you to eliminate that waste using SGLang, an open-source inference framework that caches computation already done and reuses it across future requests. When ten users share the same system prompt, SGLang processes it once, not ten times. The speedups compound quickly, especially when there's a lot of shared context across requests. Skills you'll gain: - Implement a KV cache from scratch to eliminate redundant computation within a single request - Scale caching across users and requests with RadixAttention, so shared context is only processed once - Accelerate image generation with diffusion models using SGLang's caching and multi-GPU parallelism Join and learn to make LLM inference faster and more cost-efficient at scale!

Andrew Ng

100,779 views • 4 months ago

Kyutai TTS and Unmute are now open source! The text-to-speech is natural, customizable, and fast: it can serve 32 users with a 350ms latency on a single L40S. Try it out and get started on the project page:
1:12

Kyutai TTS and Unmute are now open source! The text-to-speech is natural, customizable, and fast: it can serve 32 users with a 350ms latency on a single L40S. Try it out and get started on the project page:

kyutai

171,924 views • 1 year ago

Introducing Epic’s version control system: Lore! Built from scratch and open-sourced, we made scalability and performance core tenets from day one. We’re releasing Lore as open source today.All source code, along with documentation of data formats and protocols are released under an MIT license and free to use. Help shape it into something even more powerful, together:
0:52

Introducing Epic’s version control system: Lore! Built from scratch and open-sourced, we made scalability and performance core tenets from day one. We’re releasing Lore as open source today.All source code, along with documentation of data formats and protocols are released under an MIT license and free to use. Help shape it into something even more powerful, together:

Unreal Engine

228,396 views • 1 month ago

Demo of Tether's QVAC running local inference on a mobile device at incredible speed, via llama.cpp + LLAMA 3.2 1B parameters. QVAC is a generalized inference and fine-tuning runtime able to adapt to any device, from smartphones, to laptops and servers. Lots of models being supported already. More to come. No limits. Infinite intelligence. Coming soon
0:53

Demo of Tether's QVAC running local inference on a mobile device at incredible speed, via llama.cpp + LLAMA 3.2 1B parameters. QVAC is a generalized inference and fine-tuning runtime able to adapt to any device, from smartphones, to laptops and servers. Lots of models being supported already. More to come. No limits. Infinite intelligence. Coming soon

Paolo Ardoino 🤖

42,074 views • 1 year ago

"Imagine a 17-year-old boy built an LLM OkeyMeta from scratch" Meanwhile it is a llama3 model from Groq Inc inference via API Y'all are giving a platform and publicity to a FRAUDULENT PERSON and using age sentiment as a waiver Okechukwu Nwaozor you can not deceive everyone
0:22

"Imagine a 17-year-old boy built an LLM OkeyMeta from scratch" Meanwhile it is a llama3 model from Groq Inc inference via API Y'all are giving a platform and publicity to a FRAUDULENT PERSON and using age sentiment as a waiver Okechukwu Nwaozor you can not deceive everyone

Ebuka l Socrates🦙🐍🦜🦀

73,808 views • 8 months ago

NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses *three* NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with Modal and Pipecat AI cloud, or run locally on an NVIDIA DGX Spark or RTX 5090.
1:24

NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses *three* NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with Modal and Pipecat AI cloud, or run locally on an NVIDIA DGX Spark or RTX 5090.

kwindla

274,590 views • 7 months ago