正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Introducing FlashCompact - the first specialized model for context compaction 33k tokens/sec 200k → 50k in ~1.5s Fast, high quality compaction

Morph

3,269 subscribers

225,128 次观看 • 2 个月前 •via X (Twitter)

教育新闻政治科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Introducing Seedream 3.0, available now in the Freepik AI Suite Crazy prompt adherence, blends styles with precision, and gives fast, high-quality results Images made with this new model 🧵👇

Introducing Seedream 3.0, available now in the Freepik AI Suite Crazy prompt adherence, blends styles with precision, and gives fast, high-quality results Images made with this new model 🧵👇

Freepik

34,040 次观看 • 11 个月前

Alleviating the compaction in a few end rows while it is so dry. Rarely get this good of an opportunity. 🌽

Alleviating the compaction in a few end rows while it is so dry. Rarely get this good of an opportunity. 🌽

Brent Johnson

32,677 次观看 • 2 年前

This 30-ton autonomous planter can sow 400 hectares in 24 hours. It also significantly degrades 400 hectares of soil in 24 hours. A planter of this size aggressively compacts the soil surface and pulverizes the critical soil aggregates. Just look at the plume of topsoil left in the planter's wake. Arguably worse than surface compaction is the subsurface compaction caused by the force of a 30-ton machine traveling over the field. An initial compaction layer develops as deep as 2 feet and continues upward as new hardpan layers form on top of each other with each subsequent pass of the planter. Eventually, the subsurface compaction meets the surface compaction, and what remains is soil with no water-holding capacity, devoid of life, without the ability to cycle nutrients and generally inhospitable to crops. Despite its speed and efficiency, this planter ultimately takes the life out of farming, from the soil on up to the human operator.

This 30-ton autonomous planter can sow 400 hectares in 24 hours. It also significantly degrades 400 hectares of soil in 24 hours. A planter of this size aggressively compacts the soil surface and pulverizes the critical soil aggregates. Just look at the plume of topsoil left in the planter's wake. Arguably worse than surface compaction is the subsurface compaction caused by the force of a 30-ton machine traveling over the field. An initial compaction layer develops as deep as 2 feet and continues upward as new hardpan layers form on top of each other with each subsequent pass of the planter. Eventually, the subsurface compaction meets the surface compaction, and what remains is soil with no water-holding capacity, devoid of life, without the ability to cycle nutrients and generally inhospitable to crops. Despite its speed and efficiency, this planter ultimately takes the life out of farming, from the soil on up to the human operator.

Sam Knowlton

308,831 次观看 • 2 年前

High-quality Spatial 3D Model from the JoJoWorld creator community. The more data you contribute, the more tokens you will earn!!!

High-quality Spatial 3D Model from the JoJoWorld creator community. The more data you contribute, the more tokens you will earn!!!

JoJoWorld

33,832 次观看 • 1 年前

🔥Apple MLX first 6bit model is on Hugging Face!🔥 Qwen2.5-Coder-32B-Instruct-6bit! 3bit conversion and test in progress! Video 8x below on M4 Max 40GPU: - Prompt: 38 tokens, 61.731 tokens-per-sec - Generation: 1181 tokens, 16.939 tokens-per-sec - Peak memory: 25.122 GB

🔥Apple MLX first 6bit model is on Hugging Face!🔥 Qwen2.5-Coder-32B-Instruct-6bit! 3bit conversion and test in progress! Video 8x below on M4 Max 40GPU: - Prompt: 38 tokens, 61.731 tokens-per-sec - Generation: 1181 tokens, 16.939 tokens-per-sec - Peak memory: 25.122 GB

Ivan Fioravanti ᯅ

46,494 次观看 • 1 年前

You are not prepared for this, 250+ tokens/sec, 1B model < 2GB memory

You are not prepared for this, 250+ tokens/sec, 1B model < 2GB memory

anton

372,348 次观看 • 2 年前

Grok Code Fast 1 just shattered records on OpenRouter, crossing 237B tokens in a single day. The first model ever to move past the 200B/day milestone.

Grok Code Fast 1 just shattered records on OpenRouter, crossing 237B tokens in a single day. The first model ever to move past the 200B/day milestone.

DogeDesigner

60,691 次观看 • 7 个月前

Blackbox in Excel is now available with end-to-end encryption. • Drag & drop multiple sheets • No overwriting existing cells • Longer sessions with auto compaction

Blackbox in Excel is now available with end-to-end encryption. • Drag & drop multiple sheets • No overwriting existing cells • Longer sessions with auto compaction

BLACKBOX AI

27,289 次观看 • 4 个月前

2000 tokens/sec gives me dopamine high on opencode

2000 tokens/sec gives me dopamine high on opencode

Daniel Kim

14,504 次观看 • 8 个月前

FAST BREAK SLAM FOR THE FIRST LEAD OF THE GAME 📺 - SEC Network

FAST BREAK SLAM FOR THE FIRST LEAD OF THE GAME 📺 - SEC Network

Kentucky Men’s Basketball

32,645 次观看 • 4 个月前

introducing Seedance 2.0. the world's most powerful video model, supporting text, image, video, and even audio as input, and capable of producing long multi-shot videos with high quality. now available for everyone.

introducing Seedance 2.0. the world's most powerful video model, supporting text, image, video, and even audio as input, and capable of producing long multi-shot videos with high quality. now available for everyone.

KREA AI

43,455 次观看 • 2 个月前

Introducing Agent Tokens: • Instant global trading • Hundreds of agents integrated • $50k in $MPLX rewards Agentic Capital Markets are now live on Solana.

Introducing Agent Tokens: • Instant global trading • Hundreds of agents integrated • $50k in $MPLX rewards Agentic Capital Markets are now live on Solana.

Metaplex

258,598 次观看 • 1 个月前

First steps for a specialized DeepSeek v4 Flash inference engine focused on inference quality / stability at different quantizations, with networked API that is batching capable. This is the 2 bit quants model running on my M3 Max 128GB.

First steps for a specialized DeepSeek v4 Flash inference engine focused on inference quality / stability at different quantizations, with networked API that is batching capable. This is the 2 bit quants model running on my M3 Max 128GB.

antirez

14,155 次观看 • 1 个月前

Introducing Kraken Wallet Swaps! A fast, convenient way to swap tokens without the hassle or fees. Get the app 📲

Introducing Kraken Wallet Swaps! A fast, convenient way to swap tokens without the hassle or fees. Get the app 📲

Kraken

45,563 次观看 • 1 年前

GROK 4 FAST 2M CONTEXT – NOW IN YOUR POCKET A reasoning model with a 2M context window — rewriting the cost curve of intelligence! Here’s the Hit List: •⁠ ⁠Free on iOS and Android •⁠ ⁠Multimodal brain built for more than text •⁠ ⁠2M context leaves competitors wheezing Source: xAI

GROK 4 FAST 2M CONTEXT – NOW IN YOUR POCKET A reasoning model with a 2M context window — rewriting the cost curve of intelligence! Here’s the Hit List: •⁠ ⁠Free on iOS and Android •⁠ ⁠Multimodal brain built for more than text •⁠ ⁠2M context leaves competitors wheezing Source: xAI

Mario Nawfal

84,937 次观看 • 8 个月前

(Z.ai) is now a model provider inside TRAE. You can BYOK and add GLM-4.6 and GLM-4.5 to TRAE IDE. GLM-4.5 supports up to 128K context and GLM-4.6 expands up to 200K context. Both deliver strong coding and reasoning performance on the benchmark and offers dual “thinking/fast” modes. Available now in the latest version.

(Z.ai) is now a model provider inside TRAE. You can BYOK and add GLM-4.6 and GLM-4.5 to TRAE IDE. GLM-4.5 supports up to 128K context and GLM-4.6 expands up to 200K context. Both deliver strong coding and reasoning performance on the benchmark and offers dual “thinking/fast” modes. Available now in the latest version.

TRAE

63,501 次观看 • 7 个月前

Introducing the AI Registry Discover all models in the AI SDK AI Gateway: 🔍 Filter by: - Name - Input/output modalities - Context length - Output size - Providers 📄 View model details ⚖️ Compare model vs. model Open-source, link below!

Introducing the AI Registry Discover all models in the AI SDK AI Gateway: 🔍 Filter by: - Name - Input/output modalities - Context length - Output size - Providers 📄 View model details ⚖️ Compare model vs. model Open-source, link below!

Francisco Moretti

10,449 次观看 • 7 个月前

introducing Krea 2 Turbo. generate high-quality images in just 2s; compatible with style references, moodboards, and LoRAs. try it for free at krea . ai

introducing Krea 2 Turbo. generate high-quality images in just 2s; compatible with style references, moodboards, and LoRAs. try it for free at krea . ai

Krea

36,758 次观看 • 5 天前