Загрузка видео...

Не удалось загрузить видео

На главную

Try the first diffusion language model on the playground. Inception Labs' Mercury Coder generates over 1000 tokens/sec.

aisdk's profile picture

AI SDK

20,221 subscribers

17,964 просмотров • 1 год назад •via X (Twitter)

Наука и технологииНовости и политикаОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 5

Фото профиля AI SDK
AI SDK1 год назад

Playground:

Фото профиля Study Bunny Games
Study Bunny Games2 лет назад

Learn Japanese through "mild immersion" in a game

Фото профиля Shannon Code
Shannon Code1 год назад

@InceptionAILabs Whoa! Is playground new? It’s awesome

Фото профиля G 🏴‍☠️
G 🏴‍☠️1 год назад

@InceptionAILabs apples to oranges.. you should be comparing it more with gemini 2.0 flash given performance is more on par with that

Фото профиля BadTechBandit
BadTechBandit1 год назад

@InceptionAILabs @grok what is a diffusion language model in this context what is it useful for?

Похожие видео

Diffusion language models are SO FAST!! A new startup, Inception Labs, has released Mercury Coder, "the first commercial-scale diffusion large language model" It's 5-10x faster than current gen LLMs, providing high-quality responses at low costs. And you can try it now!
0:22

Diffusion language models are SO FAST!! A new startup, Inception Labs, has released Mercury Coder, "the first commercial-scale diffusion large language model" It's 5-10x faster than current gen LLMs, providing high-quality responses at low costs. And you can try it now!

Tanishq Mathew Abraham, Ph.D.

354,244 просмотров • 1 год назад

China's Qafind Labs just launched the first Diffusion Language Model (DLM). 🔥 ChatDLM, described as the first Diffusion Language Model (DLM), will be open-sourced soon. - Inference Speed: 2,800 tokens/sec (on A100), which is insanely fast. - Context Window: 131,072 tokens. More details 👇
0:34

China's Qafind Labs just launched the first Diffusion Language Model (DLM). 🔥 ChatDLM, described as the first Diffusion Language Model (DLM), will be open-sourced soon. - Inference Speed: 2,800 tokens/sec (on A100), which is insanely fast. - Context Window: 131,072 tokens. More details 👇

AshutoshShrivastava

73,296 просмотров • 1 год назад

Try Mercury Coder on our playground at
0:22

Try Mercury Coder on our playground at

Inception

47,097 просмотров • 1 год назад

Inception Labs just killed the transformer. They released Mercury 2, the world's first "diffusion" reasoning model. It's fast, and it uses a completely new model architecture... just watch this 11 min video to find out more:
11:35

Inception Labs just killed the transformer. They released Mercury 2, the world's first "diffusion" reasoning model. It's fast, and it uses a completely new model architecture... just watch this 11 min video to find out more:

David Ondrej

45,692 просмотров • 3 месяцев назад

Excited to share what my team has been working on lately - Gemini diffusion! We bring diffusion to language modeling, yielding more power and blazing speeds! 🚀🚀🚀 Gemini diffusion is especially strong at coding. In this example the model generates at 2000 tokens/sec, including overheads like tokenization, prefill, safety filters etc.
0:24

Excited to share what my team has been working on lately - Gemini diffusion! We bring diffusion to language modeling, yielding more power and blazing speeds! 🚀🚀🚀 Gemini diffusion is especially strong at coding. In this example the model generates at 2000 tokens/sec, including overheads like tokenization, prefill, safety filters etc.

Brendan O'Donoghue

577,625 просмотров • 1 год назад

Today's autoregressive models generate one token at a time. Mercury 2 generates tokens in parallel. Over 1,000 tok/sec on standard GPUs, at comparable quality to speed-optimized models. Since launch, the community has been showing what diffusion LLMs can unlock. Thanks to the team at Clyep for the breakdown.
3:49

Today's autoregressive models generate one token at a time. Mercury 2 generates tokens in parallel. Over 1,000 tok/sec on standard GPUs, at comparable quality to speed-optimized models. Since launch, the community has been showing what diffusion LLMs can unlock. Thanks to the team at Clyep for the breakdown.

Inception

21,104 просмотров • 1 месяц назад

We’re excited to launch Mercury, the first commercial-scale diffusion LLM tailored for chat applications! Ultra-fast and efficient, Mercury brings real-time responsiveness to conversations, just like Mercury Coder did for code.
0:56

We’re excited to launch Mercury, the first commercial-scale diffusion LLM tailored for chat applications! Ultra-fast and efficient, Mercury brings real-time responsiveness to conversations, just like Mercury Coder did for code.

Inception

90,673 просмотров • 1 год назад

BIG DAY FOR PlayAI 🚀 We’ve just open-sourced the first diffusion-LLM for speech! ⚡️ Generates audio in just 20-30 tokens (vs. 800-1000 for autoregressive) 🖌️ Perfect for super-fine in-painting edits & 🎙️ zero-shot voice cloning. Give it a try ⬇️
0:37

BIG DAY FOR PlayAI 🚀 We’ve just open-sourced the first diffusion-LLM for speech! ⚡️ Generates audio in just 20-30 tokens (vs. 800-1000 for autoregressive) 🖌️ Perfect for super-fine in-painting edits & 🎙️ zero-shot voice cloning. Give it a try ⬇️

Felfel

50,503 просмотров • 1 год назад

This is a new diffusion-based language model from Inception. I don't know how well it works compared to an autoregressive LM of a similar size, but the inference process looks badass:
0:29

This is a new diffusion-based language model from Inception. I don't know how well it works compared to an autoregressive LM of a similar size, but the inference process looks badass:

BURKOV

58,434 просмотров • 1 год назад

Stable Diffusion generates beautiful images, but can it be used for open-world recognition? Try Demo! Our #CVPR2023 paper shows that the pre-trained diffusion model indeed is a good image parser, allows for open-vocabulary segmentation and detection.
2:19

Stable Diffusion generates beautiful images, but can it be used for open-world recognition? Try Demo! Our #CVPR2023 paper shows that the pre-trained diffusion model indeed is a good image parser, allows for open-vocabulary segmentation and detection.

Xiaolong Wang

241,225 просмотров • 3 лет назад

Large Language Diffusion with Masking (LLaDA) are here - and their generation looks so fucking dope! 🤯 True to Yann LeCun's vision, Ditch the auto-regressive bits and approximate the language distribution via Maximum Likelihood Estimation! So cool to watch the model denoise text from tokens in real time! - The team released their model checkpoints and there's a demo for you to play with it too! Try it out!🤗
1:15

Large Language Diffusion with Masking (LLaDA) are here - and their generation looks so fucking dope! 🤯 True to Yann LeCun's vision, Ditch the auto-regressive bits and approximate the language distribution via Maximum Likelihood Estimation! So cool to watch the model denoise text from tokens in real time! - The team released their model checkpoints and there's a demo for you to play with it too! Try it out!🤗

Vaibhav (VB) Srivastav

21,410 просмотров • 1 год назад

NVIDIA just released AnyFlow on Hugging Face The first any-step video diffusion model that generates high-quality text-to-video with any inference budget - 4 steps or 50, quality scales smoothly without degradation.
1:17

NVIDIA just released AnyFlow on Hugging Face The first any-step video diffusion model that generates high-quality text-to-video with any inference budget - 4 steps or 50, quality scales smoothly without degradation.

DailyPapers

41,580 просмотров • 1 месяц назад

Mercury 2 is live 🚀🚀 The world’s first reasoning diffusion LLM, delivering 5x faster performance than leading speed-optimized LLMs. Watching the team turn years of research into a real product never gets old, and I’m incredibly proud of what we’ve built. We’re just getting started on what diffusion can do for language.
2:00

Mercury 2 is live 🚀🚀 The world’s first reasoning diffusion LLM, delivering 5x faster performance than leading speed-optimized LLMs. Watching the team turn years of research into a real product never gets old, and I’m incredibly proud of what we’ve built. We’re just getting started on what diffusion can do for language.

Stefano Ermon

1,035,828 просмотров • 4 месяцев назад

DeepSeek R1 (the 680B MOE) is ~20% faster in the latest mlx / mlx-lm. 4-bit model on 3 M2 Ultras generates 4k tokens at a respectable 15 toks/sec. Plus some QoL improvements: - Only downloads the local shard (much faster startup) - Distributed launcher ships with MLX
0:50

DeepSeek R1 (the 680B MOE) is ~20% faster in the latest mlx / mlx-lm. 4-bit model on 3 M2 Ultras generates 4k tokens at a respectable 15 toks/sec. Plus some QoL improvements: - Only downloads the local shard (much faster startup) - Distributed launcher ships with MLX

Awni Hannun

86,921 просмотров • 1 год назад

Introducing GDE - Grok Intergrated Development Enviroment, the first IDE optimized for blokchain incubated by Navy Labs powered by NavyAI and Grok's Large Language Model.
1:02

Introducing GDE - Grok Intergrated Development Enviroment, the first IDE optimized for blokchain incubated by Navy Labs powered by NavyAI and Grok's Large Language Model.

NavyAI

47,165 просмотров • 2 лет назад

🚀Meet Gemini Diffusion, our first diffusion-based and super fast language model, just announced at Google I/O!🚀 Very excited to be able to share what I've been working on for the past little while with our amazing small team Google DeepMind.
0:32

🚀Meet Gemini Diffusion, our first diffusion-based and super fast language model, just announced at Google I/O!🚀 Very excited to be able to share what I've been working on for the past little while with our amazing small team Google DeepMind.

Ivana Balazevic

43,472 просмотров • 1 год назад

New episode of the Information Bottleneck! We talked with Stefano Ermon about why he thinks diffusion LLMs will replace autoregressive ones. Stefano co-invented DDIM, FlashAttention, DPO, and score-based diffusion models. He's a Stanford professor and now runs Inception AI, where they built Mercury II. We go deep but also cover the bigger picture - the startup journey, PhD vs industry, and where AI is heading. A few things that stuck with me: - He thinks of autoregressive models as typewriters and diffusion models as editors. One goes left to right. The other starts messy and refines. - Mercury II (their text difussion model) already beats the fastest autoregressive models on latency-critical stuff as voice agents, code suggestions, anything where you have a tight time budget. And it does it because diffusion generates tokens in parallel instead of one at a time. - We also got into whether AI will actually replace software engineers (his answer: no), PhD vs industry advice, and what it was like going from an ICML best paper to raising money.
0:54

New episode of the Information Bottleneck! We talked with Stefano Ermon about why he thinks diffusion LLMs will replace autoregressive ones. Stefano co-invented DDIM, FlashAttention, DPO, and score-based diffusion models. He's a Stanford professor and now runs Inception AI, where they built Mercury II. We go deep but also cover the bigger picture - the startup journey, PhD vs industry, and where AI is heading. A few things that stuck with me: - He thinks of autoregressive models as typewriters and diffusion models as editors. One goes left to right. The other starts messy and refines. - Mercury II (their text difussion model) already beats the fastest autoregressive models on latency-critical stuff as voice agents, code suggestions, anything where you have a tight time budget. And it does it because diffusion generates tokens in parallel instead of one at a time. - We also got into whether AI will actually replace software engineers (his answer: no), PhD vs industry advice, and what it was like going from an ICML best paper to raising money.

Ravid Shwartz Ziv

22,350 просмотров • 3 месяцев назад

InfiniteHiP Extending Language Model Context Up to 3 Million Tokens on a Single GPU
0:53

InfiniteHiP Extending Language Model Context Up to 3 Million Tokens on a Single GPU

AK

31,240 просмотров • 1 год назад

First results are in. Llama 4 Maverick 17B active / 400B total is blazing fast with MLX on an M3 Ultra. Here is the 4-bit model generating 1100 tokens at 50 tok/sec:
0:20

First results are in. Llama 4 Maverick 17B active / 400B total is blazing fast with MLX on an M3 Ultra. Here is the 4-bit model generating 1100 tokens at 50 tok/sec:

Awni Hannun

149,855 просмотров • 1 год назад