arxiv:2305.09781
Zhihao Zhang
JackFram
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 2 months ago
TidalDecode: Fast and Accurate LLM Decoding with Position Persistent
Sparse Attention
commented
a paper
3 months ago
TidalDecode: Fast and Accurate LLM Decoding with Position Persistent
Sparse Attention
authored
a paper
3 months ago
SpecInfer: Accelerating Generative LLM Serving with Speculative
Inference and Token Tree Verification
Organizations
Papers
1
models
7
JackFram/llama-68m
Text Generation
•
Updated
•
359k
•
27
JackFram/llama-160m
Text Generation
•
Updated
•
147k
•
34
JackFram/llama-160m-base
Text Generation
•
Updated
•
30
JackFram/llama-160m-cbt-4
Text Generation
•
Updated
•
10
JackFram/llama-160m-cbt-3
Text Generation
•
Updated
•
10
JackFram/llama-160m-cbt-2
Text Generation
•
Updated
•
10
JackFram/llama-160m-cbt-1
Text Generation
•
Updated
•
11
datasets
None public yet