BackboardIO
RT @RobImbeault: What happens when the workload keeps coming?
In our GLM 5.3 sustained test at 32 concurrent users:
@BackboardIO: 370 output tokens/sec
vLLM: 74.9
4.94X aggregate output throughput.
Full model. No Quant!
0301
BackboardIO✓
@BackboardIO
inference. pre-training. post-training. quant.
23 Following319 Followers1.5K Posts
- BackboardIORT @RobImbeault: Our latest GLM 5.3 full-model BF16 test: @BackboardIO: 165.5 output tokens/sec vLLM: 63.5 output tokens/sec 2.61X aggregate output throughput. Same 96 workflows. Same request bodies. 32 concurrent users.0301
- Backboard just got a little more powerful. ⚡ 35 new media tools. More reliable video generation. Better usage reporting. Plus a few product improvements. Read the full update →010166
- AI infrastructure doesn’t become valuable when the API works. It becomes valuable when the system works in production. That means connecting infrastructure to a real outcome and proving it works. Our thinking on benchmarks →000244
- Agent memory is becoming infrastructure. The hard part isn’t storing more history. It’s deciding what should persist, who can use it, how it changes, and when it should disappear. We’ve been exploring that architecture at Backboard →314138
- #BackboardAsks: What's one AI feature everyone is hyping that you think becomes a commodity in a year? 👀00278
- The model will change. Your application state shouldn’t have to. Backboard’s approach keeps memory and orchestration portable across models and providers instead of tying the application to one runtime. More on the layers around the model →00260
- Jev by @typesafeai AI is now on Backboard. ⚡ @HackTheNorth is happening, so skip the waitlist and use Jev through the Backboard API while you build. Find us at Hack the North this weekend. 👀 We can’t wait to see what you cook up.
025616 - Jev by @typesafeai is now available on Backboard API. More instructions coming soon this isn’t your typical LLM. And we have no doubt that it will be part of our open source CLI and IDE soon!017659
- Realtime voice-to-voice is now live on Backboard. 🎙️ Agents can now listen, respond, remember, and use tools in realtime. OpenAI, Gemini, and Grok voice models are supported, with persistent conversations and Backboard tools built in.
126216 - Video generation just dropped. 🎥 AI so good it gave us 1,000 aura points. 😎 (+10,000 aura points for @RobImbeault's bald spot.) There’s a lot more in this release 👀 → Improved image generation → More media inputs → Video editing + extension → More control over generation → Updated Model Library → SDK updates119161
- New models alert! ⚡ Backboard’s model catalog keeps expanding automatically as new options become available. Now available through OpenRouter:
015126 - Stateful routing is becoming an important part of AI infrastructure. Instead of routing every request in isolation, it carries context forward so execution can adapt based on what happened earlier in the workflow. See how Backboard approaches it → #BuildWithBackboard01296
- We can feel it. @BackboardDevsa16z @a16zastra waiting to get added to the model selector dropdown004155
- BackboardIORT @BackboardDevs: Gemini 3.8 is now on Backboard Studio.
Google @GoogleIntroducing Gemini 3.8, our best reasoning & coding model yet. By leveraging long-running agentic loops, we’re building on the momentum of 3.7 Flash from just three weeks ago to release two new 3.8 variants: Meet Gemini 3.8 Flash and Gemini 3.8 Flash Cyber 🧵0101 
- Show more posts
