正在加载视频...

视频加载失败

返回首页

Here is how to deploy and serve any LLM on HF with a single command in less than 3 minutes with llama.cpp $ bash -c "$(curl -s

ggerganov's profile picture

Georgi Gerganov

63,062 subscribers

143,145 次观看 • 2 年前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

8 条评论

Georgi Gerganov 的头像
Georgi Gerganov2 年前

More info

Fernando Vidal 的头像
Fernando Vidal2 年前

Would be cool to have some kind of auth system, where you can have it check against a list of auth tokens before serving the request.

Donneker 的头像
Donneker2 年前

thanks for the demo, nice done

bornjre 的头像
bornjre2 年前

Does server binary supports LLaVA/BakLLaVA models ?

wwwwg 的头像
wwwwg2 年前

@memdotai mem it

Mem 的头像
Mem2 年前

@ggerganov Saved! Here's the compiled thread: 🪄 AI-generated summary: "This thread provides instructions on how to deploy and serve any LLM on HF with a single command in less than 3 minutes using llama.cpp. More information can be found at the...

Tim Wu 的头像
Tim Wu2 年前

Time to fill up my runpod credits. 😁 It would be lovely if supports llava.

Filippo Broggini 的头像
Filippo Broggini2 年前

They should have made you CEO of OpenAI 😅😇💪

相关视频

Deploy Custom Oracle Feeds In 97 Seconds On SEDA. Watch CTO jasper: - Configure a feed. - Deploy a feed. - Execute request with results In less than 2 minutes....
1:39

Deploy Custom Oracle Feeds In 97 Seconds On SEDA. Watch CTO jasper: - Configure a feed. - Deploy a feed. - Execute request with results In less than 2 minutes....

SEDA

54,189 次观看 • 1 年前

How to instantly get more FPS in ANY GAME with the TunedPC App in less than 4 minutes:
4:22

How to instantly get more FPS in ANY GAME with the TunedPC App in less than 4 minutes:

KIRNEILL

73,472 次观看 • 5 个月前

🦞 Ready to deploy OpenClaw🦞? Our just released NVIDIA NemoClaw simplifies running OpenClaw always-on assistants more safely with a single command. ✅ Deploy claws more safely ✅ Run any coding agent ✅ Deploy anywhere Try with a free NVIDIA Brev Launchable: 🔗
2:33

🦞 Ready to deploy OpenClaw🦞? Our just released NVIDIA NemoClaw simplifies running OpenClaw always-on assistants more safely with a single command. ✅ Deploy claws more safely ✅ Run any coding agent ✅ Deploy anywhere Try with a free NVIDIA Brev Launchable: 🔗

NVIDIA AI Developer

189,810 次观看 • 4 个月前

Analyzing your LinkedIn data with ChatGPT's Code Interpreter is a secret weapon. 🤫 Use it to identify your next customer or job opportunity in less than 10 minutes. Here is a quick tutorial on how.
8:03

Analyzing your LinkedIn data with ChatGPT's Code Interpreter is a secret weapon. 🤫 Use it to identify your next customer or job opportunity in less than 10 minutes. Here is a quick tutorial on how.

Sebo ⚛︎

73,754 次观看 • 2 年前

BIG MAN TD ALERT!! Saint Francis Football S&C Sophomore Jared Almeida with the focus to tie it up with less than 2 minutes in regulation. #SCTop10 ESPNAssignmentDesk NAIAFBALL
0:31

BIG MAN TD ALERT!! Saint Francis Football S&C Sophomore Jared Almeida with the focus to tie it up with less than 2 minutes in regulation. #SCTop10 ESPNAssignmentDesk NAIAFBALL

ISC Sports Network

24,176 次观看 • 1 年前

Creating & deploying a dapp on Fuel is easy, and fast. Watch me start from scratch, add a feature, and deploy that dapp to testnet in less than 2 minutes ⚡️👇
1:52

Creating & deploying a dapp on Fuel is easy, and fast. Watch me start from scratch, add a feature, and deploy that dapp to testnet in less than 2 minutes ⚡️👇

Dhai

21,085 次观看 • 1 年前

How to improve your bullet registration on any FPS Game and increase your K/D in less than 2 minutes *Sips Tea*☕️
1:31

How to improve your bullet registration on any FPS Game and increase your K/D in less than 2 minutes *Sips Tea*☕️

KIRNEILL

138,665 次观看 • 2 年前

The truck is able to repair potholes in less than five minutes each and is capable of fixing up to 50 potholes in a single day.
1:21

The truck is able to repair potholes in less than five minutes each and is capable of fixing up to 50 potholes in a single day.

Tech Burrito

573,674 次观看 • 3 年前

Agents & MCP are great... but how can you DEPLOY an agent with MCP tools? Here's the fastest way I've found to build and deploy with the OpenAI Agents SDK in <3 minutes.
3:46

Agents & MCP are great... but how can you DEPLOY an agent with MCP tools? Here's the fastest way I've found to build and deploy with the OpenAI Agents SDK in <3 minutes.

matt palmer

64,690 次观看 • 1 年前

Someone built a free and better alternative to Claude that runs 100% locally. → works with any LLM (Claude, GPT, Gemini, vLLM) → beats it on deep research → has Cowork-like capabilities → 50+ connectors out of the box → deploy in literally one command 100% open source. MIT license. 28k stars.
1:00

Someone built a free and better alternative to Claude that runs 100% locally. → works with any LLM (Claude, GPT, Gemini, vLLM) → beats it on deep research → has Cowork-like capabilities → 50+ connectors out of the box → deploy in literally one command 100% open source. MIT license. 28k stars.

How To Prompt

39,303 次观看 • 3 个月前

anyways here's USC vs Notre Dame on 4th and 9 with USC down 3 with less than 2 minutes left in the 4th quarter ✌🏻
0:34

anyways here's USC vs Notre Dame on 4th and 9 with USC down 3 with less than 2 minutes left in the 4th quarter ✌🏻

Arrogant Nation✌🏻

13,577 次观看 • 3 个月前

I'm super excited to launch ⌘ 🥳 ⌘ Langbase – Composable AI developer platform to ship AI features in minutes, not months. Deploy AI Pipes: Hook any LLM to any data, hyper-personalized API AI Memory: Managed search engine API with RAG tools
12:59

I'm super excited to launch ⌘ 🥳 ⌘ Langbase – Composable AI developer platform to ship AI features in minutes, not months. Deploy AI Pipes: Hook any LLM to any data, hyper-personalized API AI Memory: Managed search engine API with RAG tools

Ahmad Awais

57,484 次观看 • 2 年前

GPT-4o's native image gen enables amazing workflows You can generate the perfect landing page with 4o and then build and deploy it with Replit. Literally from imagination to production in less than 5 minutes. Prompts below
0:34

GPT-4o's native image gen enables amazing workflows You can generate the perfect landing page with 4o and then build and deploy it with Replit. Literally from imagination to production in less than 5 minutes. Prompts below

Paul Couvert

290,720 次观看 • 1 年前

Most "AI coding tools" need 5 files, a build config, and a prayer. Gradio 6's gr.HTML: one Python file. Frontend, backend, state—done 😎 Generate with Claude or any frontier LLM in one shot. Deploy in seconds. This is what vibe coding is supposed to be! Full breakdown👇️
0:28

Most "AI coding tools" need 5 files, a build config, and a prayer. Gradio 6's gr.HTML: one Python file. Frontend, backend, state—done 😎 Generate with Claude or any frontier LLM in one shot. Deploy in seconds. This is what vibe coding is supposed to be! Full breakdown👇️

Gradio

22,392 次观看 • 5 个月前

he literally taught me how to bersyukur dan ikhlas in less than 3 minutes
2:21

he literally taught me how to bersyukur dan ikhlas in less than 3 minutes

tubina

343,091 次观看 • 2 年前

MARVEL SNAP Beach Bash is here, and ⁨Ken is here to show you how to get tubular with Sub-Mariner!
5:19

MARVEL SNAP Beach Bash is here, and ⁨Ken is here to show you how to get tubular with Sub-Mariner!

MARVEL SNAP

15,252 次观看 • 2 个月前

Homemade marshmallow! Made with just a few ingredients and in less than ten minutes.
1:49

Homemade marshmallow! Made with just a few ingredients and in less than ten minutes.

Mindful DIY

57,951 次观看 • 3 个月前

Build a multiplayer game from your terminal! Billy Jacobson shows how to vibe code a holiday village and deploy it with real-time syncing using the /𝚏𝚒𝚛𝚎𝚋𝚊𝚜𝚎 𝚒𝚗𝚒𝚝 command in Gemini CLI. From local script to live URL in minutes → #DEVcember
1:28

Build a multiplayer game from your terminal! Billy Jacobson shows how to vibe code a holiday village and deploy it with real-time syncing using the /𝚏𝚒𝚛𝚎𝚋𝚊𝚜𝚎 𝚒𝚗𝚒𝚝 command in Gemini CLI. From local script to live URL in minutes → #DEVcember

Google Cloud Tech

11,810 次观看 • 8 个月前