https://t.co/orcApi6B7J
You can now easily load various pre-quantized models (block FP8, NVFP4, AWQ/GPTQ/HQQ, certain GGUFs) via a vLLM plugin! You can also run on-the-fly quant as well, easy to use: 1 or 2 flags to enable!
Open sourcing something fun from @Dropbox: Witchcraft.
It's a local search engine built in Rust with no API keys or vector DB required.
Think: ColBERT / late interaction style retrieval, but packaged to run locally (perfect for coding agents).
Let's dive in👇
This was a great talk at DSpy meetup about how Dropbox optimized their search relevance judge:
https://t.co/Wx7hx2pobY
Also available in blog post form:
https://t.co/V2nI5PSA2G
DSpy both improved structural conformance of SLM output (valid JSON) and agreement with humans (NMSE).
Wow! Quite a detailed blog from @Dropbox on how they optimize Dropbox Dash relevance judge with @DSPyOSS.
Shout out to the Dropbox Dash team Eric Wang, Dmitriy Meyerzon, and @joshclemm !
hmm isn't it obvious this would work better than QAT? I’ve been doing this already for HQQ+, the DeepSeek re-distill work, and FP4 weight quant quality recovery. More comments below 🧵
If you’re at @EurIPSConf this week and looking for your next ML role, ping us. Few of us from @Dropbox including @mobicham@appughar will be there Happy to chat about roles in multimodal, search, and video-AI.
Looking for people with experience in : Building and scaling multimodal ML systems, Retrieval, ranking, and creative search problems, Turning prototypes into polished products
🌍 Remote (Germany or Denmark)
Apply here: https://t.co/utBstvNyM4 (Please use the link, not DMs!)
Looking for people with experience in : Building and scaling multimodal ML systems, Retrieval, ranking, and creative search problems, Turning prototypes into polished products
🌍 Remote (Germany or Denmark)
Apply here: https://t.co/utBstvNyM4 (Please use the link, not DMs!)
We are looking for a Machine Learning Engineer (IC3) to join our Multimedia AI team at Dropbox!
You’ll work on the ML behind Dropbox Dash, building real multimodal search experiences across images, video, and text — and ship things that millions of people actually use.
And for my fellow nerds: with Dash, we're obsessed with depth of context, not just breadth. Dash isn't just calling APIs and doing naive keyword search. We build a full semantic index of all your content that is natively multimodal: not just documents but images, videos, everything.
This is the only way to build true understanding and close the context gap to make AI actually useful at work.
The best AI apps need the right context and @Dropbox Dash is built to provide it.
Thrilled to welcome the incredible tech and talent from @Mobius_Labs to the team.
Multimodal AI will make the Dash context platform even stronger 💪
@Dropbox Keep supporting us, keep an eye on what's next, give Dropbox Dash a spin… or come join us to take this search + AI revolution to the next level. https://t.co/VDPhpDTYlI
Kinda disappointed by Qwen3-VL's decoder perf with vLLM so far. Can squeeze better perf via GemLite instead of DeepGEMM but the numbers still seem suspiciously low