SparQ Attention: Bandwidth-Efficient LLM Inference
Paper
•
2312.04985
•
Published
•
39
closeAI
llama-ultra-producer
·
AI & ML interests
machine learning infra developer
Recent Activity
new activity
2 days ago
nvidia/DeepSeek-R1-FP4:Benchmark results compared to orig fp8 / int4 quants etc?
liked
a model
2 days ago
SGLang/DeepSeek-V3-NextN
new activity
3 days ago
nvidia/DeepSeek-R1-FP4:Benchmark results compared to orig fp8 / int4 quants etc?
Organizations
None yet
llama-ultra-producer's activity
upvoted
a
paper
7 months ago
upvoted
an
article
8 months ago
Article
Hugging Face on AMD Instinct MI300 GPU
•
12