Eldar Kurtić's picture

25 5 2

Eldar Kurtić

ekurtic

·

AI & ML interests

Efficient inference

Recent Activity

updated a model 4 days ago

ekurtic/lossless-lm-dev-uniform-bw4

published a model 4 days ago

ekurtic/lossless-lm-dev-uniform-bw4

updated a model 10 days ago

ekurtic/Qwen3-8B-kvattn-fp8-tensor

View all activity

Organizations

Papers 14

arxiv:2411.02355

arxiv:2410.14649

arxiv:2407.10994

arxiv:2405.15593

spaces 1

Test

models 16

ekurtic/lossless-lm-dev-uniform-bw4

Updated 4 days ago

ekurtic/Qwen3-8B-kvattn-fp8-tensor

8B • Updated 10 days ago • 11

ekurtic/Qwen3-8B-kvattn-fp8-attn_head

8B • Updated 10 days ago • 8

ekurtic/Llama-3.1-8B-Instruct-kvattn-fp8-tensor

8B • Updated 10 days ago • 9

ekurtic/Llama-3.1-8B-Instruct-kvattn-fp8-attn_head_layer1_4q2kv

Updated 10 days ago • 10

ekurtic/Llama-3.1-8B-Instruct-kvattn-fp8-attn_head_layer1

Updated 10 days ago • 10

ekurtic/Llama-3.1-8B-Instruct-kvattn-fp8-attn_head

8B • Updated 10 days ago • 10

ekurtic/Llama-2-7b-chat-hf-kvattn-fp8-tensor

7B • Updated 10 days ago • 10

ekurtic/Llama-2-7b-chat-hf-kvattn-fp8-attn_head

7B • Updated 10 days ago • 11

ekurtic/qwen3-8b-int4-asym

2B • Updated 12 days ago • 6

datasets 0

None public yet