https://github.com/vllm-project/vllm/releases/tag/v0.9.2
they added Gemma 3n (but with text part yet)
#vllm #nlp
they added Gemma 3n (but with text part yet)
#vllm #nlp
GitHub
Release v0.9.2 · vllm-project/vllm
Highlights
This release contains 452 commits from 167 contributors (31 new!)
NOTE: This is the last version where V0 engine code and features stay intact. We highly recommend migrating to V1 engine...
This release contains 452 commits from 167 contributors (31 new!)
NOTE: This is the last version where V0 engine code and features stay intact. We highly recommend migrating to V1 engine...
doing something
https://github.com/vllm-project/vllm/releases/tag/v0.9.2 they added Gemma 3n (but with text part yet) #vllm #nlp
tg_image_1833827235.png
177 KB
vLLM can't run the model as library but it works well with
Also, run it on >= Ada architectures, V0 engine doesn't start the model
#vllm #gemma
serve commandAlso, run it on >= Ada architectures, V0 engine doesn't start the model
#vllm #gemma
👍2
https://www.liquid.ai/blog/liquid-foundation-models-v2-our-second-series-of-generative-ai-models
#llm
#llm
Liquid AI
Introducing LFM2: The Fastest On-Device Foundation Models on the Market | Blog
Today, we release LFM2, a new class of Liquid Foundation Models (LFMs) that sets a new standard in quality, speed, and memory efficiency for on-device deployment. Built on a hybrid architecture, LFM2 delivers 200% faster decode and prefill performance than…