Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing Parallel Requests for MLX! Multiple requests to the same model can now be processed simultaneously ✨🚄⚡️ Works both in the API and in Split View chats. See it in action 👇🕺

LM Studio

60,936 subscribers

40,805 views • 7 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Vibe Design is all about rapid iteration. Now your tools finally move as fast as your ideas. 🌍✨ Introducing Parallel Editing. ⚡️ Iterate across multiple screens at the same time. You can now fire off edits on multiple screens simultaneously—or spin up 5 different edits of the same screen at once. While "vibe coding" makes you wait line-by-line, Stitch lets you iterate on your entire flow in parallel. Don’t block your creativity.

Vibe Design is all about rapid iteration. Now your tools finally move as fast as your ideas. 🌍✨ Introducing Parallel Editing. ⚡️ Iterate across multiple screens at the same time. You can now fire off edits on multiple screens simultaneously—or spin up 5 different edits of the same screen at once. While "vibe coding" makes you wait line-by-line, Stitch lets you iterate on your entire flow in parallel. Don’t block your creativity.

Stitch by Google

73,103 views • 9 months ago

We took a 30B model and split it in two to write tokens in parallel instead of one at a time. Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch. We found it kept 98.7% of the original model’s quality at 2.42× faster generation.

We took a 30B model and split it in two to write tokens in parallel instead of one at a time. Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch. We found it kept 98.7% of the original model’s quality at 2.42× faster generation.

NVIDIA AI

762,357 views • 2 months ago

Hermes can now search and extract the web on a fresh install with zero API keys. Behind the scenes, it rotates requests across the public free tiers from Exa, Parallel, Tavily, Firecrawl, and Keenable. If one provider rate limits, Hermes automatically tries the next. Configured backends and API keys still take priority. The keyless ring is a last resort fallback, not guaranteed infrastructure, and it can be disabled entirely.

Hermes can now search and extract the web on a fresh install with zero API keys. Behind the scenes, it rotates requests across the public free tiers from Exa, Parallel, Tavily, Firecrawl, and Keenable. If one provider rate limits, Hermes automatically tries the next. Configured backends and API keys still take priority. The keyless ring is a last resort fallback, not guaranteed infrastructure, and it can be disabled entirely.

Hybrid 🏃🏾

10,589 views • 1 month ago

The op kept it for 6 yrs and just uploaded it this March. There were two kisses: the one in the new video should be the ‘first’ one (you can see the same male staff in both video)

The op kept it for 6 yrs and just uploaded it this March. There were two kisses: the one in the new video should be the ‘first’ one (you can see the same male staff in both video)

Kaede711

209,117 views • 4 months ago

Introducing bunnyOS: the small-model agent and inference platform. Small language models can now reason, plan, use tools, and take action. We are building the infrastructure to unlock them. Litepaper in bio.

Introducing bunnyOS: the small-model agent and inference platform. Small language models can now reason, plan, use tools, and take action. We are building the infrastructure to unlock them. Litepaper in bio.

Bunny Open Society

325,887 views • 2 months ago

OpenAI is working on a new experimental feature for Codex called Scratchpad. Users will be able to start multiple Codex chats from a TODO list view, which will be executed in parallel. It will become very instrumental in the upcoming Codex Superapp, where you will be able to trigger a broader range of tasks to achieve your goals. * Not available yet 👀

OpenAI is working on a new experimental feature for Codex called Scratchpad. Users will be able to start multiple Codex chats from a TODO list view, which will be executed in parallel. It will become very instrumental in the upcoming Codex Superapp, where you will be able to trigger a broader range of tasks to achieve your goals. * Not available yet 👀

🚨 AI News | TestingCatalog

313,642 views • 5 months ago

Introducing Private Swaps. You can now privately swap supported tokens on Privacy Cash, powered by the same protocol that has already processed $173M+ in private transfers, and passed 14 audits.

Introducing Private Swaps. You can now privately swap supported tokens on Privacy Cash, powered by the same protocol that has already processed $173M+ in private transfers, and passed 14 audits.

Privacy Cash

326,016 views • 8 months ago

Crosschain Swaps are live! Today, we are introducing the Across Swap API for crosschain swaps in a single call. Bridge and Swap are now one action.

Crosschain Swaps are live! Today, we are introducing the Across Swap API for crosschain swaps in a single call. Bridge and Swap are now one action.

Across

43,442 views • 1 year ago

Example of how it works in Layout Inspector (now embedded in Running Devices window). One can view counts and change the recomposition color as well, defaults to Blue.

Example of how it works in Layout Inspector (now embedded in Running Devices window). One can view counts and change the recomposition color as well, defaults to Blue.

Chris Sinco

20,168 views • 1 year ago

Today I'm launching a very early release of MLX Model Manager ( A Swift package for quickly and easily adding LLM/VLMs with just a couple of lines of code into your MacOS/iOS applications for local and private inferencing. This is built on the amazing work of the MLX team & what they have done with MLX Model Manager unifies the work they have done with MLXLLM as well as MLXVLM into one package with added abstractions to simplify the usage. I've also added support for Google's new Paligemma2 Vision Model ( You can see a demonstration in the video below! Huge shoutout to Awni Hannun for the creation of MLX, David Koski on leading the charge for MLXVLM and Prince Canuma for the creation of MLX-VLM. Three massive pillars in the MLX community among many others.

Today I'm launching a very early release of MLX Model Manager ( A Swift package for quickly and easily adding LLM/VLMs with just a couple of lines of code into your MacOS/iOS applications for local and private inferencing. This is built on the amazing work of the MLX team & what they have done with MLX Model Manager unifies the work they have done with MLXLLM as well as MLXVLM into one package with added abstractions to simplify the usage. I've also added support for Google's new Paligemma2 Vision Model ( You can see a demonstration in the video below! Huge shoutout to Awni Hannun for the creation of MLX, David Koski on leading the charge for MLXVLM and Prince Canuma for the creation of MLX-VLM. Three massive pillars in the MLX community among many others.

Kunal Batra

104,815 views • 1 year ago

New free plugin in the works. ⚙️ Create expression controls for multiple params on multiple layers in one click. Would it be useful in your workflow? Working title Expression Driver. Try it free now on our discord. #aftereffects #aescripts #motiondesign

New free plugin in the works. ⚙️ Create expression controls for multiple params on multiple layers in one click. Would it be useful in your workflow? Working title Expression Driver. Try it free now on our discord. #aftereffects #aescripts #motiondesign

Plugin Everything

10,197 views • 1 year ago

Introducing MLX-Swift-TS An SDK for running time series foundation models fully on-device on Apple Silicon. When I joined Datadog, Inc. , I was introduced to Toto, our time series foundation model, and got excited about zero-shot forecasting across different domains. While building a health copilot app, I realized there wasn’t a simple way to run models like these locally on device. So I built one. MLX-Swift-TS exposes a common TimeSeriesForecaster interface for loading and running multiple time series architectures directly in Swift using MLX. No server required. The attached video shows on-device forecasting running inside a native Swift app. Huge thanks to Awni Hannun and the MLX team for building MLX and its Swift API, Prince Canuma for inspiration on MLX SDK patterns, and Ameet Talwalkar and the Datadog team for Toto.

Introducing MLX-Swift-TS An SDK for running time series foundation models fully on-device on Apple Silicon. When I joined Datadog, Inc. , I was introduced to Toto, our time series foundation model, and got excited about zero-shot forecasting across different domains. While building a health copilot app, I realized there wasn’t a simple way to run models like these locally on device. So I built one. MLX-Swift-TS exposes a common TimeSeriesForecaster interface for loading and running multiple time series architectures directly in Swift using MLX. No server required. The attached video shows on-device forecasting running inside a native Swift app. Huge thanks to Awni Hannun and the MLX team for building MLX and its Swift API, Prince Canuma for inspiration on MLX SDK patterns, and Ameet Talwalkar and the Datadog team for Toto.

Kunal Batra

12,585 views • 6 months ago

Perplexity Computer is massively multi-model. Computer orchestrates models to run agents in parallel, leveraging Opus to match each task to the model best suited for it. In total, Computer can route work across 19 different models.

Perplexity Computer is massively multi-model. Computer orchestrates models to run agents in parallel, leveraging Opus to match each task to the model best suited for it. In total, Computer can route work across 19 different models.

Perplexity

534,569 views • 6 months ago

Sending and receiving requests in the upcoming Xaman® Wallet 🪝 version: Request in any issued asset too, not only the native asset. And thanks to Pathfinding, the request can be paid in any other currency. You'll recieve what you asked for. Oh and network aware 💪

Sending and receiving requests in the upcoming Xaman® Wallet 🪝 version: Request in any issued asset too, not only the native asset. And thanks to Pathfinding, the request can be paid in any other currency. You'll recieve what you asked for. Oh and network aware 💪

Wietse Wind - 🪝🛠 Xaman® + XRPL + Xahau

75,610 views • 1 year ago

📢Introducing HertzFlow Alpha Skill: See What Insiders See Drop any Binance Alpha CA to get full on-chain forensic &insights crystal clear in mins Your AI agent can now see what MMs don't want you to see — powered by @surfdeveloper the only API you need for crypto research 👇

📢Introducing HertzFlow Alpha Skill: See What Insiders See Drop any Binance Alpha CA to get full on-chain forensic &insights crystal clear in mins Your AI agent can now see what MMs don't want you to see — powered by @surfdeveloper the only API you need for crypto research 👇

HertzFlow | Mainnet Arc🎲

168,269 views • 3 months ago