Загрузка видео...

Не удалось загрузить видео

На главную

Ollama 0.2 is here! Concurrency is now enabled by default. This unlocks 2 major features: Parallel requests Ollama can now serve multiple requests at the same time, using only a little bit of additional memory for each request. This enables use cases such as: - Handling multiple chat sessions...

ollama's profile picture

ollama

183,303 subscribers

219,459 просмотров • 2 лет назад •via X (Twitter)

Наука и технологииНовости и политика
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 11

Фото профиля Augustinas Malinauskas
Augustinas Malinauskas2 лет назад

This is super cool! Ollama will go in history for making AI easily accessible!🔥

Фото профиля ollama
ollama2 лет назад

Let's make the future together! Look back at history later. 🤣 Time to build!! ❤️❤️❤️ Love your work!

Фото профиля Robert Avram
Robert Avram2 лет назад

Game changer you guys are the best in the game

Фото профиля ollama
ollama2 лет назад

Here to serve! 😍 Thank you for supporting Ollama

Фото профиля hidE ☢️
hidE ☢️2 лет назад

Coincidentally today I was going to add concurrency for my agents in golang. And I didn't know if ollama would support it or not. Now I know it will.

Фото профиля ollama
ollama2 лет назад

so awesome! ❤️ Let us know how it goes for you. We're here to listen to feedback.

Фото профиля King 👑 Cyril 🧠
King 👑 Cyril 🧠2 лет назад

LFG 🚀

Фото профиля ollama
ollama2 лет назад

Go go go!! 🚀🚀🚀

Фото профиля Mike Bird (Hiring)
Mike Bird (Hiring)2 лет назад

Way to go Ollama team!

Фото профиля Jush@1Ghz
Jush@1Ghz2 лет назад

finally thank you

Фото профиля ollama
ollama2 лет назад

😍 please support Ollama!

Похожие видео

Cursor now natively supports git worktrees. You can run multiple agents in parallel, each with their own isolated copy of the codebase. This is great for comparing models or running the same model multiple times and picking the best result.
0:42

Cursor now natively supports git worktrees. You can run multiple agents in parallel, each with their own isolated copy of the codebase. This is great for comparing models or running the same model multiple times and picking the best result.

Lee Robinson

157,666 просмотров • 11 месяцев назад

Ollama can now think! 🤔🤔🤔 For thinking models, and especially useful for very thoughtful models like DeepSeek-R1-0528, Ollama can separate the thoughts and the response. Thinking can also be disabled! This is useful for getting a direct response. This works across Ollama's CLI, API, and Python/JavaScript libraries. 🧵 blog post 👇👇👇
1:38

Ollama can now think! 🤔🤔🤔 For thinking models, and especially useful for very thoughtful models like DeepSeek-R1-0528, Ollama can separate the thoughts and the response. Thinking can also be disabled! This is useful for getting a direct response. This works across Ollama's CLI, API, and Python/JavaScript libraries. 🧵 blog post 👇👇👇

ollama

106,316 просмотров • 1 год назад

DeepSeek R1 671B is ridiculously good, but running at 158 tokens per second is something out of this world. A model *this good* running *this fast* is 3 years ahead of this time. The secret: DeepSeek in this short video isn't running on GPUs. It's running on custom-made chips! This is running on SambaNova and their SN40L chips, which are designed and optimized for running AI workflows. SambaNova is sponsoring my work. We designed GPUs to run games and later realized we could use them for AI. This is very different from creating a chip specifically for AI from the ground up. Just think about this for a second: One single SNL40 chip can simultaneously hold 100+ models (trillions of parameters) in memory! An agentic workflow that uses multiple models simultaneously won't need to swap models from memory even once! By the way, the Llama family of models *screams* on the SambaNova Cloud. Here are some numbers from my latest tests: • Llama 3.3 70B: 367.32 t/s • Llama 3.2 1B: 2381.82 t/s • Llama 3.2 3B: 1335.71 t/s • Llama 3.1 8B: 929.58 t/s • Llama 3.1 70B: 369.16 t/s • Llama 3.1 405B: 103.37 t/s You can access all of these models for free!
1:34

DeepSeek R1 671B is ridiculously good, but running at 158 tokens per second is something out of this world. A model *this good* running *this fast* is 3 years ahead of this time. The secret: DeepSeek in this short video isn't running on GPUs. It's running on custom-made chips! This is running on SambaNova and their SN40L chips, which are designed and optimized for running AI workflows. SambaNova is sponsoring my work. We designed GPUs to run games and later realized we could use them for AI. This is very different from creating a chip specifically for AI from the ground up. Just think about this for a second: One single SNL40 chip can simultaneously hold 100+ models (trillions of parameters) in memory! An agentic workflow that uses multiple models simultaneously won't need to swap models from memory even once! By the way, the Llama family of models *screams* on the SambaNova Cloud. Here are some numbers from my latest tests: • Llama 3.3 70B: 367.32 t/s • Llama 3.2 1B: 2381.82 t/s • Llama 3.2 3B: 1335.71 t/s • Llama 3.1 8B: 929.58 t/s • Llama 3.1 70B: 369.16 t/s • Llama 3.1 405B: 103.37 t/s You can access all of these models for free!

Santiago

131,099 просмотров • 1 год назад

Maximizing your token throughput is one of the biggest productivity unlocks in Claude Code. So here's my guide to use multiple Claude Codes at the same time, effectively: - Run multiple Claude Code sessions at the same time, each on a different feature (Ghostty is great for this) - Use Claude Code's built in git worktrees to keep each instance isolated on its own branch (-w or --worktree flag) - Let Claude handle creating PRs or merging the worktree branches when you're done - Use the Claude Code Desktop app as your multi-agent control center Full guide below:
2:44

Maximizing your token throughput is one of the biggest productivity unlocks in Claude Code. So here's my guide to use multiple Claude Codes at the same time, effectively: - Run multiple Claude Code sessions at the same time, each on a different feature (Ghostty is great for this) - Use Claude Code's built in git worktrees to keep each instance isolated on its own branch (-w or --worktree flag) - Let Claude handle creating PRs or merging the worktree branches when you're done - Use the Claude Code Desktop app as your multi-agent control center Full guide below:

Avthar

10,754 просмотров • 6 месяцев назад

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail
3:02

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

LangChain

33,192 просмотров • 1 год назад

ClickUp is working on a Cowork feature 👀 > Cowork can help users build, edit, and take action alongside them, and other agents at the same time > Sessions are persistent, so context carries across the entire workday > Multiple users can collaborate in the same Brain session simultaneously Brain Cowork can proactively work in the channel just like a human teammate, drafting docs and setting reminders in the same thread where the team is actively working.
0:20

ClickUp is working on a Cowork feature 👀 > Cowork can help users build, edit, and take action alongside them, and other agents at the same time > Sessions are persistent, so context carries across the entire workday > Multiple users can collaborate in the same Brain session simultaneously Brain Cowork can proactively work in the channel just like a human teammate, drafting docs and setting reminders in the same thread where the team is actively working.

🚨 AI News | TestingCatalog

24,249 просмотров • 4 месяцев назад

Open models are already being used in the enterprise. Over 85% of the Fortune 500 companies already use Ollama to fulfill specific tasks. Jeffrey Morgan Why open models and Ollama? Ownership. Open models are yours to keep, customize, and optimize. Affordable. Run it the way you like, in your own environment. Private. Your data belongs to you.
1:37

Open models are already being used in the enterprise. Over 85% of the Fortune 500 companies already use Ollama to fulfill specific tasks. Jeffrey Morgan Why open models and Ollama? Ownership. Open models are yours to keep, customize, and optimize. Affordable. Run it the way you like, in your own environment. Private. Your data belongs to you.

ollama

43,242 просмотров • 2 месяцев назад

This is the fastest I've seen Llama 3.3 running anywhere! Llama 3.3 70B running at 652 t/s is lightning fast. And if you want Llama 3.1, here are the speeds I was able to get: • Llama 3.1 8B: 1006 t/s • Llama 3.1 70B: 709 t/s • Llama 3.1 405B: 206 t/s (You can access all of these models for free! See the link below.) This speed is incredible, but the interesting part is what's happening behind the scenes: These models aren't running on a GPU! In this video, I'm using the SambaNova cloud to access these models. They built a custom chip (SN40L) optimized for AI workflows. A single SN40L chip can hold hundreds of models (trillions of parameters) in memory! The speed alone is a huge deal, but the big advantage is for agentic workflows running multiple specialized models. A GPU can only host a single model and switch (unload and load) to a different model if necessary. An SN40L, on the other hand, can host every model at once, making it much faster. Here is the video where you can see how fast these chips are:
7:24

This is the fastest I've seen Llama 3.3 running anywhere! Llama 3.3 70B running at 652 t/s is lightning fast. And if you want Llama 3.1, here are the speeds I was able to get: • Llama 3.1 8B: 1006 t/s • Llama 3.1 70B: 709 t/s • Llama 3.1 405B: 206 t/s (You can access all of these models for free! See the link below.) This speed is incredible, but the interesting part is what's happening behind the scenes: These models aren't running on a GPU! In this video, I'm using the SambaNova cloud to access these models. They built a custom chip (SN40L) optimized for AI workflows. A single SN40L chip can hold hundreds of models (trillions of parameters) in memory! The speed alone is a huge deal, but the big advantage is for agentic workflows running multiple specialized models. A GPU can only host a single model and switch (unload and load) to a different model if necessary. An SN40L, on the other hand, can host every model at once, making it much faster. Here is the video where you can see how fast these chips are:

Santiago

97,561 просмотров • 1 год назад

“Our compute nodes don’t run a full copy of the models we train on IOTA. They actually run a small sliver of the model. This means you can train really large frontier sized models using very small building blocks”. CTO crux unpacks how IOTA ・ SN9’s model parallel architecture allows us to train at scale by splitting our models across multiple machines, and then sewing them together. This is core to SN9’s architecture. See the full Eye On A.I. podcast below.
0:36

“Our compute nodes don’t run a full copy of the models we train on IOTA. They actually run a small sliver of the model. This means you can train really large frontier sized models using very small building blocks”. CTO crux unpacks how IOTA ・ SN9’s model parallel architecture allows us to train at scale by splitting our models across multiple machines, and then sewing them together. This is core to SN9’s architecture. See the full Eye On A.I. podcast below.

IOTA ・ SN9

15,465 просмотров • 4 месяцев назад

EIGHT USED RTX 3090s. 192GB OF VRAM. ONE PRIVATE BOX BUILT TO RUN 70B AI MODELS WITHOUT RENTING A DATACENTER. 00:06 the team lowers all eight GPUs into the chassis at once, turning a pile of old gaming cards into the core of a serious local AI server. each 3090 contributes 24GB of memory. combined, the rack has enough VRAM for heavyweight models, large document collections, long context and multiple jobs running side by side. these cards are five years old, but AI economics work differently from gaming. memory capacity matters more than having the newest badge, which is why used 3090s remain valuable. the server can keep one model loaded while separate GPUs handle video, images, transcription and overnight agents without sending private company data into the cloud. bookmark this build before yesterday’s gaming GPUs become tomorrow’s cheapest AI infrastructure.
0:29

EIGHT USED RTX 3090s. 192GB OF VRAM. ONE PRIVATE BOX BUILT TO RUN 70B AI MODELS WITHOUT RENTING A DATACENTER. 00:06 the team lowers all eight GPUs into the chassis at once, turning a pile of old gaming cards into the core of a serious local AI server. each 3090 contributes 24GB of memory. combined, the rack has enough VRAM for heavyweight models, large document collections, long context and multiple jobs running side by side. these cards are five years old, but AI economics work differently from gaming. memory capacity matters more than having the newest badge, which is why used 3090s remain valuable. the server can keep one model loaded while separate GPUs handle video, images, transcription and overnight agents without sending private company data into the cloud. bookmark this build before yesterday’s gaming GPUs become tomorrow’s cheapest AI infrastructure.

Gipp 🦅

119,018 просмотров • 3 месяцев назад

Ever heard of Connected Lenses on Spectacles ? Because together is more fun and this is a little glimpse into the future of AR. Connected Lenses let multiple people run the same Lens and share + save data across devices, whether you’re side by side or miles apart. That means you can build AR experiences your friends can jump into at the same time, then return to later, with the world still remembering what you all did.
29:29

Ever heard of Connected Lenses on Spectacles ? Because together is more fun and this is a little glimpse into the future of AR. Connected Lenses let multiple people run the same Lens and share + save data across devices, whether you’re side by side or miles apart. That means you can build AR experiences your friends can jump into at the same time, then return to later, with the world still remembering what you all did.

Alessio

79,134 просмотров • 8 месяцев назад

Pocket TTS goes multilingual! Now you can use our 100M-parameter models to generate speech in six languages, fast enough to run real-time without a GPU. We also improved the quality of the English model while keeping the same size. And all of this is open-source.
0:28

Pocket TTS goes multilingual! Now you can use our 100M-parameter models to generate speech in six languages, fast enough to run real-time without a GPU. We also improved the quality of the English model while keeping the same size. And all of this is open-source.

kyutai

30,012 просмотров • 5 месяцев назад

Ollama v0.33 is here! You can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider. One toggle. Cloud & local models just work👇
0:28

Ollama v0.33 is here! You can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider. One toggle. Cloud & local models just work👇

ollama

495,403 просмотров • 1 месяц назад

Today Paper has something special to share Tabs are live in Paper ✨ This is a big deal because you and your agent can now work on multiple files at the same time. Unblock parallel prompting: explore faster, stay in flow, stay creative (sound on for the video! 🔊)
0:32

Today Paper has something special to share Tabs are live in Paper ✨ This is a big deal because you and your agent can now work on multiple files at the same time. Unblock parallel prompting: explore faster, stay in flow, stay creative (sound on for the video! 🔊)

Stephen Haney

205,729 просмотров • 1 месяц назад

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!
1:37

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

Andrew Ng

162,196 просмотров • 6 месяцев назад

Introducing Klok, a next-gen AI chat app built using Mira's Infra. You can now use multiple frontier models on Klok for all your AI needs within the same chat, all while also earning Mira points. AI must be democratized, and Klok is taking big steps to ensure that.
0:26

Introducing Klok, a next-gen AI chat app built using Mira's Infra. You can now use multiple frontier models on Klok for all your AI needs within the same chat, all while also earning Mira points. AI must be democratized, and Klok is taking big steps to ensure that.

Mira

180,187 просмотров • 1 год назад

ChatGPT Voice is now in the desktop app. Control your computer and direct multiple agents running in ChatGPT Work or Codex, using just your voice. It's powered by GPT-Live, so it can speak, listen, and coordinate work in the app at the same time. Rolling out globally today on macOS and Windows to Plus, Pro, Business, Edu, and Enterprise plans.
1:08

ChatGPT Voice is now in the desktop app. Control your computer and direct multiple agents running in ChatGPT Work or Codex, using just your voice. It's powered by GPT-Live, so it can speak, listen, and coordinate work in the app at the same time. Rolling out globally today on macOS and Windows to Plus, Pro, Business, Edu, and Enterprise plans.

OpenAI

4,742,982 просмотров • 2 месяцев назад

🚨 You can use GPT-6 Astra as the orchestrator and DeepSeek V4.1 Flash as the agents to cut costs by more than 88% while maintaining the same level of quality. And now it’s even better, since DeepSeek V4.1 Flash is one of the best models for cybersecurity at an incredibly low price
0:40

🚨 You can use GPT-6 Astra as the orchestrator and DeepSeek V4.1 Flash as the agents to cut costs by more than 88% while maintaining the same level of quality. And now it’s even better, since DeepSeek V4.1 Flash is one of the best models for cybersecurity at an incredibly low price

Iam_

32,627 просмотров • 23 дней назад

U.S. open-source models are quickly gaining ground. @Nvidia's newest Nemotron Ultra is fast growing on Ollama and unlocking complex, longer running tasks for developers
0:41

U.S. open-source models are quickly gaining ground. @Nvidia's newest Nemotron Ultra is fast growing on Ollama and unlocking complex, longer running tasks for developers

ollama

74,064 просмотров • 2 месяцев назад