Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference
Junyan Li
senfu
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
FlowCompile: An Optimizing Compiler for Structured LLM Workflows submitted a paper about 2 months ago
FlowCompile: An Optimizing Compiler for Structured LLM Workflows updated a dataset 11 months ago
senfu/testOrganizations
models 27
senfu/Llama-3.1-8B-Instruct-CommVQ-2bit-codebook
Updated
senfu/Llama-3.1-8B-Instruct-CommVQ-1bit-codebook
Updated
senfu/Llama-3.1-8B-Instruct-CommVQ-1bit
8B • Updated • 7
senfu/DeepSeek-R1-Distill-Qwen-32B-BG
Text Generation • 33B • Updated • 4
senfu/Qwen3-8B-BG
Text Generation • 9B • Updated • 37
senfu/DeepSeek-R1-Distill-Qwen-7B-BG
Text Generation • 8B • Updated • 77 • 1
senfu/Llama-3.1-8B-Instruct-CommVQ-2bit
9B • Updated • 14
senfu/llava-v1.5-7b-flexattn
Text Generation • 8B • Updated • 6 • 1
senfu/test_7b
Updated
senfu/covlm-2.8b
Updated • 1