lu

janelu

·

janelu9

AI & ML interests

Large Model, Parallel Computing

Recent Activity

new activity about 1 month ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ3_S: 2 x RTX 5060 Ti 16 GB, prefill - 1200 t/s | decoding - 60 t/s | context - 262k

new activity about 2 months ago

prism-ml/Ternary-Bonsai-2-27B-gguf:How well does this model perform on agentic tasks?

liked a model about 2 months ago

prism-ml/Ternary-Bonsai-2-27B-gguf

View all activity

Organizations

New activity in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF about 1 month ago

IQ3_S: 2 x RTX 5060 Ti 16 GB, prefill - 1200 t/s | decoding - 60 t/s | context - 262k

#42 opened about 1 month ago by

New activity in prism-ml/Ternary-Bonsai-2-27B-gguf about 2 months ago

How well does this model perform on agentic tasks?

#15 opened about 2 months ago by

liked a model about 2 months ago

prism-ml/Ternary-Bonsai-2-27B-gguf

Text Generation • 27B • Updated 8 days ago • 1.54M • 3k

authored a paper 6 months ago

Periodic Asynchrony: An On-Policy Approach for Accelerating LLM Reinforcement Learning

Paper • 2511.18871 • Published Apr 28