arxiv:2412.11689
Zmushko Philip
fzmushko
AI & ML interests
None yet
Recent Activity
upvoted a paper about 23 hours ago
Disaggregated Quantization: Specializing LLM Prefill and Decode submitted a paper 3 months ago
One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining upvoted a paper 5 months ago
MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-TuningOrganizations
None yet
