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.

Congrats on the TypeScript 7 release! 🎉 TS7 vs TS6 racing Hono RPC type inference - tsc is 3-4x faster!! (Not 10x: that's parse + multi-core over many files - Hono's inference is one deep sequential type)

Yusuke Wada

27,065 subscribers

25,315 views • 3 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

5 Comments

Yusuke Wada3 months ago

`tsc --extendedDiagnostics` on the same 400-route app: Check time: 0.89s => 0.29s (3.1x) Total time: 1.03s => 0.31s (3.3x) Instantiations: 668k => 1.32M (2x more!) Fun fact: tsgo performs 2x the type instantiations and still finishes 3x faster.

joel 🐞3 months ago

was gonna complain how ts 7 still seemed slow and then i saw the ts 6 version lol

Felipe Fumero1 month ago

Being precise that it's 3-4x on a single deep sequential inference, not the marketed 10x from parallel parsing, is the kind of detail that actually makes the benchmark trustworthy. What's the isolated inference case you tested?

Tifan3 months ago

🤯🤯

0vr3uC3 months ago

My project is 7.7x, very impressive

Related Videos

🚀 10x Faster TypeScript in VS Code! TypeScript 7.0 is here, a 10x faster native port of TypeScript. Download the new VS Code extension today to get started! #visualstudiocode #vscodeextensions #typescript

🚀 10x Faster TypeScript in VS Code! TypeScript 7.0 is here, a 10x faster native port of TypeScript. Download the new VS Code extension today to get started! #visualstudiocode #vscodeextensions #typescript

Visual Studio Code

101,624 views • 3 months ago

Hindley Milner type inference (algorithm-j) visualized 🎉

Hindley Milner type inference (algorithm-j) visualized 🎉

🦋 Jared Forsyth

39,893 views • 3 years ago

type inference from .sql files has been achieved internally ORMs are toast

type inference from .sql files has been achieved internally ORMs are toast

colinhacks

392,332 views • 13 days ago

We are just a little bit faster than@nvidia GPUs on Qwen 235B...18X faster. inference is blazing fast...come build cool stuff on Cerebras inference

We are just a little bit faster than@nvidia GPUs on Qwen 235B...18X faster. inference is blazing fast...come build cool stuff on Cerebras inference

Andrew Feldman

44,760 views • 1 year ago

We've begun work on a native port of the TypeScript compiler and tools. ✅ 10x faster build times ✅ Reduced memory usage ✅ Faster editor startup and command-line type-checking by mid-2025 Learn more:

We've begun work on a native port of the TypeScript compiler and tools. ✅ 10x faster build times ✅ Reduced memory usage ✅ Faster editor startup and command-line type-checking by mid-2025 Learn more:

Microsoft Developer

22,615 views • 1 year ago

you are NOT wrong Theo - t3.gg it is a VERY big deal! TypeScript 7 is 4x faster than TS 6, confirmed by our own internal testing. Most teams can't migrate yet breaking changes, monorepo risk, team buy in. WebStorm, a JetBrains IDE lets you get TS7 performance right now! even if your project is still on 5.4. Here's how it works. 🧵

you are NOT wrong Theo - t3.gg it is a VERY big deal! TypeScript 7 is 4x faster than TS 6, confirmed by our own internal testing. Most teams can't migrate yet breaking changes, monorepo risk, team buy in. WebStorm, a JetBrains IDE lets you get TS7 performance right now! even if your project is still on 5.4. Here's how it works. 🧵

Jason Torres

15,613 views • 3 months ago

Nvidia just revealed Vera Rubin. Ships H2 2026. The numbers are wild: → 10x more performance per watt vs Blackwell → 10x cheaper inference token cost → 4x fewer GPUs to train the same MoE model Energy was the biggest bottleneck in AI. Nvidia just made it 10x cheaper.

Nvidia just revealed Vera Rubin. Ships H2 2026. The numbers are wild: → 10x more performance per watt vs Blackwell → 10x cheaper inference token cost → 4x fewer GPUs to train the same MoE model Energy was the biggest bottleneck in AI. Nvidia just made it 10x cheaper.

Min Choi

285,639 views • 8 months ago

$TAO is tackling the core challenges in machine learning, from optimizing data collection to faster inference, aiming to outperform giants like OpenAI and Microsoft. With a focus on computational efficiency and robust models, the race is on.

$TAO is tackling the core challenges in machine learning, from optimizing data collection to faster inference, aiming to outperform giants like OpenAI and Microsoft. With a focus on computational efficiency and robust models, the race is on.

Grayscale

88,595 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

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

DiffusionKit now supports Stable Diffusion 3 Medium MLX Python and Core ML Swift Inference work great for on-device inference on Mac! MLX: Core ML: Mac App: Hugging Face Diffusers App (Pending App Store review)

DiffusionKit now supports Stable Diffusion 3 Medium MLX Python and Core ML Swift Inference work great for on-device inference on Mac! MLX: Core ML: Mac App: Hugging Face Diffusers App (Pending App Store review)

argmax

74,009 views • 2 years ago

what if you could instantly clone any object? Gemma 4 is now on @Cerebras Inference, running up to 10x faster than GPUs (1,500 tokens/sec). Multimodal generations you can iterate on in real time :)

what if you could instantly clone any object? Gemma 4 is now on @Cerebras Inference, running up to 10x faster than GPUs (1,500 tokens/sec). Multimodal generations you can iterate on in real time :)

Sarah Chieng

33,279 views • 4 months ago

🚨FLUX.1 Kontext [dev], the open image editing model, is now available at fal with training capabilities! ✨4x faster inference (2s vs 7s) 💰 Ultra-affordable at $0.025/megapixel 🔧 Full LoRA training support 🖌️Game-changing image editing capabilities

🚨FLUX.1 Kontext [dev], the open image editing model, is now available at fal with training capabilities! ✨4x faster inference (2s vs 7s) 💰 Ultra-affordable at $0.025/megapixel 🔧 Full LoRA training support 🖌️Game-changing image editing capabilities

fal

161,022 views • 1 year 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

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 • 7 months ago

LFM2-Audio just dropped! It's a 1.5B model that understands and generates both text and audio Inference 10x faster + quality on par with models 10x larger Available today on Hugging Face and our playground 🥳

LFM2-Audio just dropped! It's a 1.5B model that understands and generates both text and audio Inference 10x faster + quality on par with models 10x larger Available today on Hugging Face and our playground 🥳

Maxime Labonne

85,053 views • 1 year ago

Treating every inference request the same is lighting money on fire. DigitalOcean Inference Router sends each request to the right model automatically–lower cost, faster response, and no quality tradeoff. Open-source engine. Drop-in API. Live since April. ✨

Treating every inference request the same is lighting money on fire. DigitalOcean Inference Router sends each request to the right model automatically–lower cost, faster response, and no quality tradeoff. Open-source engine. Drop-in API. Live since April. ✨

DigitalOcean

595,422 views • 5 months ago

Crusoe Managed Inference is now available. Run model inference faster, easier, and more cost-effectively. Large-context AI solutions demand fast outputs, massive throughput, and resilient scaling. Crusoe Managed Inference delivers breakthrough speed & reduced input-token spend.

Crusoe Managed Inference is now available. Run model inference faster, easier, and more cost-effectively. Large-context AI solutions demand fast outputs, massive throughput, and resilient scaling. Crusoe Managed Inference delivers breakthrough speed & reduced input-token spend.

Crusoe

12,096,815 views • 11 months ago

Ex-vLLM core contributor explained how to make LLM inference 10x cheaper in 34 minutes - better than $3000 inference optimization bootcamps. request comes in -> check LMCache -> hit? load KV cache from CPU/SSD/remote -> skip prefill -> serve. That loop is why Bloomberg and other production stacks now push 300 terabytes of KV cache per week. LMCache + vLLM + CPU/SSD/remote storage + zero-copy CUDA kernels - that's the stack. Watch and save it, then wire the KV-offload into your inference stack.

Ex-vLLM core contributor explained how to make LLM inference 10x cheaper in 34 minutes - better than $3000 inference optimization bootcamps. request comes in -> check LMCache -> hit? load KV cache from CPU/SSD/remote -> skip prefill -> serve. That loop is why Bloomberg and other production stacks now push 300 terabytes of KV cache per week. LMCache + vLLM + CPU/SSD/remote storage + zero-copy CUDA kernels - that's the stack. Watch and save it, then wire the KV-offload into your inference stack.

h100envy

61,470 views • 3 months ago

introducing fast inference ( fast inference is an LLM API for devs who want to go faster access the fastest Kimi K3, GLM, DeepSeek, etc for $9/mo integrations with Claude Code, Codex, OpenCode & more speeds compounds. waiting for Claude does not

introducing fast inference ( fast inference is an LLM API for devs who want to go faster access the fastest Kimi K3, GLM, DeepSeek, etc for $9/mo integrations with Claude Code, Codex, OpenCode & more speeds compounds. waiting for Claude does not

Sam Hogan 🇺🇸

159,780 views • 2 months ago

1/ $AMD is a 10x opportunity everybody ignores. Lisa Su believes that inference will be a bigger market than training. Training is the cost center of AI workload while inference is where you make money. $AMD has an advantage here. Let me explain why: 🧵

1/ $AMD is a 10x opportunity everybody ignores. Lisa Su believes that inference will be a bigger market than training. Training is the cost center of AI workload while inference is where you make money. $AMD has an advantage here. Let me explain why: 🧵

Oguz Erkan

413,275 views • 1 year ago