Kirill
hypothetical
AI & ML interests
DNNs, differential geometry, algebraic topology, cryptography
Recent Activity
reacted
to
their
post
with 🚀
about 3 hours ago
We thought it would be easier, but finally we have integrated CuDNN Paged Attention to our models!
Read article here: https://app.thestage.ai/blog/Integrating-cuDNN-Paged-Attention-to-TheStage-AI-Inference?id=8
Llama-8B with CuDNN paged attention, including B200 support: https://huggingface.co/TheStageAI/Elastic-Llama-3.1-8B-Instruct
Mistral-Small-24B with CuDNN paged attention, including B200 support: https://huggingface.co/TheStageAI/Elastic-Mistral-Small-3.1-24B-Instruct-2503
posted
an
update
about 3 hours ago
We thought it would be easier, but finally we have integrated CuDNN Paged Attention to our models!
Read article here: https://app.thestage.ai/blog/Integrating-cuDNN-Paged-Attention-to-TheStage-AI-Inference?id=8
Llama-8B with CuDNN paged attention, including B200 support: https://huggingface.co/TheStageAI/Elastic-Llama-3.1-8B-Instruct
Mistral-Small-24B with CuDNN paged attention, including B200 support: https://huggingface.co/TheStageAI/Elastic-Mistral-Small-3.1-24B-Instruct-2503
liked
a Space
about 4 hours ago
neuphonic/neutts-nano
Organizations