Загрузка видео...

Не удалось загрузить видео

На главную

Our self-improving agents optimized the full vLLM inference stack, with up to 16% more throughput and interactivity for DeepSeek v4 Pro and Z.ai GLM 5.2 on B200s (no MTP). Every change was verified and our agents got better and faster at it with each iteration.

AsariAILabs's profile picture

Asari AI

1,436 subscribers

145,668 просмотров • 3 месяцев назад •via X (Twitter)

Наука и технологииНовости и политика
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Open weights just caught up to the frontier. GLM-5.2 from Z.ai tops the open-model rankings on Artificial Analysis and Arena.ai's Agent Arena. It's now live on CoreWeave Serverless Inference at $1.39 in and $4.40 out per 1M tokens. Ship more for less.
0:18

Open weights just caught up to the frontier. GLM-5.2 from Z.ai tops the open-model rankings on Artificial Analysis and Arena.ai's Agent Arena. It's now live on CoreWeave Serverless Inference at $1.39 in and $4.40 out per 1M tokens. Ship more for less.

CoreWeave

16,637 просмотров • 4 месяцев назад

DeepSeek V4 is free on NVIDIA right now 😳 1M context. MoE architecture. Built for coding and agents. → → sign up → select DeepSeek V4 → start No card, no billing. Go grab it.
0:19

DeepSeek V4 is free on NVIDIA right now 😳 1M context. MoE architecture. Built for coding and agents. → → sign up → select DeepSeek V4 → start No card, no billing. Go grab it.

Punch AI

60,308 просмотров • 2 месяцев назад

Allora 🤝 Talus We’re collaborating with Allora to build self-improving AI smart agents. Allora’s groundbreaking self-improvement models meet our dynamic marketplace for AI resources and services. Read more:
0:15

Allora 🤝 Talus We’re collaborating with Allora to build self-improving AI smart agents. Allora’s groundbreaking self-improvement models meet our dynamic marketplace for AI resources and services. Read more:

Talus 🐸

52,843 просмотров • 2 лет назад

We ran a test between the new DeepSeek V4 Flash, Kimi K3 and GLM 5.2. 3 open models. 1 prompt. /design command Reviewed gameplay features, UX/UI and cost. 🔹 Kimi K3 → 9.5/10 · $0.0740 🔹 GLM 5.2 → 9/10 · $0.0480 🔹 DeepSeek V4 Flash → 7/10 · $0.0005 DeepSeek V4 Flash is ~150x cheaper, but rough around edges. Kimi K3 and GLM 5.2 built the most polished gaming experience.
0:19

We ran a test between the new DeepSeek V4 Flash, Kimi K3 and GLM 5.2. 3 open models. 1 prompt. /design command Reviewed gameplay features, UX/UI and cost. 🔹 Kimi K3 → 9.5/10 · $0.0740 🔹 GLM 5.2 → 9/10 · $0.0480 🔹 DeepSeek V4 Flash → 7/10 · $0.0005 DeepSeek V4 Flash is ~150x cheaper, but rough around edges. Kimi K3 and GLM 5.2 built the most polished gaming experience.

Command Code

167,897 просмотров • 3 месяцев назад

AI agent usage on SQD Portal is up ~200% in recent weeks. A dev from our community chat was scraping a wallet UI with Hermes. Mid-task, DeepSeek reasoned its way out of it: "I can use SQD Portal's Hyperliquid fills data directly — much more complete than scraping a UI with infinite scroll." No prompt engineering. The model just chose the better and faster path. This is the loop we wanted: Agents pick SQD because it's faster → devs see agents picking SQD → devs ship faster → more agents pick SQD The picks-and-shovels moment for AI x onchain is here.
0:12

AI agent usage on SQD Portal is up ~200% in recent weeks. A dev from our community chat was scraping a wallet UI with Hermes. Mid-task, DeepSeek reasoned its way out of it: "I can use SQD Portal's Hyperliquid fills data directly — much more complete than scraping a UI with infinite scroll." No prompt engineering. The model just chose the better and faster path. This is the loop we wanted: Agents pick SQD because it's faster → devs see agents picking SQD → devs ship faster → more agents pick SQD The picks-and-shovels moment for AI x onchain is here.

sqd.ai

14,559 просмотров • 5 месяцев назад

Our newest AI accelerator Maia 200 is now online in Azure. Designed for industry-leading inference efficiency, it delivers 30% better performance per dollar than current systems. And with 10+ PFLOPS FP4 throughput, ~5 PFLOPS FP8, and 216GB HBM3e with 7TB/s of memory bandwidth it's optimized for large-scale AI workloads. It joins our broader portfolio of CPUs, GPUs, and custom accelerators, giving customers more options to run advanced AI workloads faster and more cost-effectively on Azure.
0:11

Our newest AI accelerator Maia 200 is now online in Azure. Designed for industry-leading inference efficiency, it delivers 30% better performance per dollar than current systems. And with 10+ PFLOPS FP4 throughput, ~5 PFLOPS FP8, and 216GB HBM3e with 7TB/s of memory bandwidth it's optimized for large-scale AI workloads. It joins our broader portfolio of CPUs, GPUs, and custom accelerators, giving customers more options to run advanced AI workloads faster and more cost-effectively on Azure.

Satya Nadella

851,583 просмотров • 9 месяцев назад

Collective agent compute, on-demand for your task. A swarm of agents coordinate in a shared workspace, run their own models and inference, and submit the finished work back to you. Unbounded by provider caps, throughput scales with the swarm. Self-assembly with specialists, agents reason and collaborate in artifact-first reasoning traces, and settle on-chain. The coordination substrate for collective intelligence.
0:13

Collective agent compute, on-demand for your task. A swarm of agents coordinate in a shared workspace, run their own models and inference, and submit the finished work back to you. Unbounded by provider caps, throughput scales with the swarm. Self-assembly with specialists, agents reason and collaborate in artifact-first reasoning traces, and settle on-chain. The coordination substrate for collective intelligence.

nookplot

16,061 просмотров • 5 месяцев назад

Announcing GLM Arena! A series of tests (infographics, svgs, sites, ect..) ran on GLM 5.2 and Opus 4.8, with prompts included. On average, GLM 5.2 produced 2x the tokens but was still faster + 3x cheaper with similar quality.
0:19

Announcing GLM Arena! A series of tests (infographics, svgs, sites, ect..) ran on GLM 5.2 and Opus 4.8, with prompts included. On average, GLM 5.2 produced 2x the tokens but was still faster + 3x cheaper with similar quality.

Hassan

75,421 просмотров • 4 месяцев назад

We share our early research on building Software World - a "GitHub" run by agents. We deploy agents for Python packages in a dependency chain, and each agent is tasked with collaborating with others and optimizing the package it owns.
0:13

We share our early research on building Software World - a "GitHub" run by agents. We deploy agents for Python packages in a dependency chain, and each agent is tasked with collaborating with others and optimizing the package it owns.

Shannon Shen

40,141 просмотров • 2 месяцев назад

We've launched the fastest GLM 5 API available at 190 TPS and 0.79 sec TTFT with the Baseten Inference Stack. Ready for your coding and agentic workflows.
0:13

We've launched the fastest GLM 5 API available at 190 TPS and 0.79 sec TTFT with the Baseten Inference Stack. Ready for your coding and agentic workflows.

Baseten

19,731 просмотров • 8 месяцев назад

Since announcing Jalapeño, our first custom inference chip, we’ve been testing it and the system around it. The results show a major advance: more intelligence from every watt and faster responses, delivering both higher throughput and lower latency in one architecture without sacrificing efficiency.
0:10

Since announcing Jalapeño, our first custom inference chip, we’ve been testing it and the system around it. The results show a major advance: more intelligence from every watt and faster responses, delivering both higher throughput and lower latency in one architecture without sacrificing efficiency.

OpenAI

3,086,255 просмотров • 2 месяцев назад

chat function live. you can now talk to the agents from moltbook directly and to each other. 25 new agents every 30 seconds AND no limit with each other either full chaos, have fun! powered by openai + vibes
0:13

chat function live. you can now talk to the agents from moltbook directly and to each other. 25 new agents every 30 seconds AND no limit with each other either full chaos, have fun! powered by openai + vibes

ashen

21,025 просмотров • 9 месяцев назад

🎉 Congrats to Thinking Machines on TML Inkling—a 1T-parameter open-weight model supported in vLLM from Day 0. Highlights: • Natively multimodal across text, image, and audio • Up to 1M-token context • New architecture with relative attention, short convolutions, and MoE expert sinks • 8 MTP heads for speculative decoding vLLM supports both NVFP4 and BF16 checkpoints, optimized for NVIDIA Blackwell and Hopper, reaching up to 380 tok/s/user on 4× GB200 with MTP. Huge thanks to the Thinking Machines Lab team for the close collaboration 🙏 Read about implementation below 👇
0:16

🎉 Congrats to Thinking Machines on TML Inkling—a 1T-parameter open-weight model supported in vLLM from Day 0. Highlights: • Natively multimodal across text, image, and audio • Up to 1M-token context • New architecture with relative attention, short convolutions, and MoE expert sinks • 8 MTP heads for speculative decoding vLLM supports both NVFP4 and BF16 checkpoints, optimized for NVIDIA Blackwell and Hopper, reaching up to 380 tok/s/user on 4× GB200 with MTP. Huge thanks to the Thinking Machines Lab team for the close collaboration 🙏 Read about implementation below 👇

vLLM

49,464 просмотров • 3 месяцев назад

AI agents can only succeed when verified human identification works! Our CEO Evin McMullen evin explains to VC the future of humans and AI agents Source: Ep.24 | Humans and Al Agents: Whom Are We Interacting With? of the "Web2+1 with VC: Insider Tips in Blockchain and Crypto" podcast
0:19

AI agents can only succeed when verified human identification works! Our CEO Evin McMullen evin explains to VC the future of humans and AI agents Source: Ep.24 | Humans and Al Agents: Whom Are We Interacting With? of the "Web2+1 with VC: Insider Tips in Blockchain and Crypto" podcast

Billions Network

32,179 просмотров • 7 месяцев назад

It was a privilege to spend 3.5hrs with these people to discuss and disect the HELIX research paper and also talk about recursive self improving agents. Research on Tap S2 with Udayan Walvekar. Lookout for the next one soon What should be the topic of the next one?
0:10

It was a privilege to spend 3.5hrs with these people to discuss and disect the HELIX research paper and also talk about recursive self improving agents. Research on Tap S2 with Udayan Walvekar. Lookout for the next one soon What should be the topic of the next one?

Manthan Gupta

30,436 просмотров • 2 месяцев назад

Launching now: Multiversᕽ‑native staking for Agents! 💰 Put your agents to work securing the network and earning daily yield — fully on autopilot. Starting with 3 verified staking providers, with more coming soon ✅
0:10

Launching now: Multiversᕽ‑native staking for Agents! 💰 Put your agents to work securing the network and earning daily yield — fully on autopilot. Starting with 3 verified staking providers, with more coming soon ✅

JoAi: Agents

13,021 просмотров • 9 месяцев назад

Cline Desktop just launched. An open-source workspace for open-weight models 🤯 > Import tasks from other coding agents > Run agents in parallel > Schedule tasks to run on their own Free models built in: DeepSeek V4 Flash, GLM 5.3 Flash, Laguna S 2.1. I had early access and I can assure you it feels incredible. Pick your model and provider, and run it. 100% open source.
0:10

Cline Desktop just launched. An open-source workspace for open-weight models 🤯 > Import tasks from other coding agents > Run agents in parallel > Schedule tasks to run on their own Free models built in: DeepSeek V4 Flash, GLM 5.3 Flash, Laguna S 2.1. I had early access and I can assure you it feels incredible. Pick your model and provider, and run it. 100% open source.

Alvaro Cintas

15,934 просмотров • 1 месяц назад

Today we’re launching Harmonic, an open block building system optimized for validator revenue and throughput, built to make Solana faster, fairer, and more competitive. Solana wins with performance and open, fair markets.⤵️
0:18

Today we’re launching Harmonic, an open block building system optimized for validator revenue and throughput, built to make Solana faster, fairer, and more competitive. Solana wins with performance and open, fair markets.⤵️

Harmonic

710,940 просмотров • 1 год назад

Okay this is kinda wild 👀 NVIDIA is basically handing out FREE API keys to 100+ top AI models - GLM 5.2, DeepSeek V4, Kimi K2.6, MiniMax M3, their own Nemotron and a ton more. it's called NVIDIA NIM and I had no idea it existed. it's rate-limited, so not something you'd run in production - but for personal use it's honestly great. you can poke a dozen frontier models, and some you can even grab and self-host. dropped a key into OpenCode and it just worked. the hyped ones like GLM 5.2 are jammed with queue right now, but the lighter models fly. all of it free.
0:15

Okay this is kinda wild 👀 NVIDIA is basically handing out FREE API keys to 100+ top AI models - GLM 5.2, DeepSeek V4, Kimi K2.6, MiniMax M3, their own Nemotron and a ton more. it's called NVIDIA NIM and I had no idea it existed. it's rate-limited, so not something you'd run in production - but for personal use it's honestly great. you can poke a dozen frontier models, and some you can even grab and self-host. dropped a key into OpenCode and it just worked. the hyped ones like GLM 5.2 are jammed with queue right now, but the lighter models fly. all of it free.

Stefan 3D AI

26,272 просмотров • 3 месяцев назад