PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters
Paper
•
2504.08791
•
Published
•
132
Tang
Shengkun
AI & ML interests
None yet
Recent Activity
updated
a model
about 1 month ago
Shengkun/Qwen3-16B-A2B-Pruned
published
a model
about 1 month ago
Shengkun/Qwen3-16B-A2B-Pruned
updated
a model
about 2 months ago
Shengkun/DarwinLM-4.6B-Llama3.1-8B-Pruned-Masked
Organizations
None yet
Shengkun's activity
upvoted
a
paper
2 months ago
upvoted
3
papers
4 months ago
DarwinLM: Evolutionary Structured Pruning of Large Language Models
Paper
•
2502.07780
•
Published
•
18
HALO: Hadamard-Assisted Lossless Optimization for Efficient Low-Precision LLM Training and Fine-Tuning
Paper
•
2501.02625
•
Published
•
16
QuEST: Stable Training of LLMs with 1-Bit Weights and Activations
Paper
•
2502.05003
•
Published
•
44