IST Austria Distributed Algorithms and Systems Lab

university

https://ist.ac.at/en/research/alistarh-group/

https://github.com/IST-DASLab

AI & ML interests

None defined yet.

Recent Activity

SpiridonSunRotator authored a paper 9 days ago

FLAMIA: FLAsh MIcroscaling Attention for Fast and Causally Safe Training on Blackwell

SpiridonSunRotator submitted a paper 9 days ago

FLAMIA: FLAsh MIcroscaling Attention for Fast and Causally Safe Training on Blackwell

kwanhee new activity 9 days ago

ISTA-DASLab/Kimi-K3-P48NVFP4-MoESQ:Kimi K3 GSQ-RCO-GGUF IQ1_S, IQ1_M, IQ2_XXS

View all activity

Papers

Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts

WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms

View all Papers

ISTA-DASLab 's models 144

ISTA-DASLab/gemma-2-9b-HIGGS-4bit

Text Generation • 3B • Updated Dec 6, 2024 • 9

ISTA-DASLab/gemma-2-9b-it-HIGGS-3bit

Text Generation • 3B • Updated Dec 6, 2024 • 6

ISTA-DASLab/gemma-2-9b-it-HIGGS-4bit

Text Generation • 3B • Updated Dec 6, 2024 • 8 • 1

ISTA-DASLab/Llama-3.2-3B-Instruct-AQLM-PV-2Bit-2x8

Text Generation • 1B • Updated Nov 8, 2024 • 12

ISTA-DASLab/Llama-3.2-3B-AQLM-PV-2Bit-2x8

Text Generation • 1B • Updated Nov 8, 2024 • 34

ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16

Text Generation • 2B • Updated Nov 8, 2024 • 60 • 12

ISTA-DASLab/Meta-Llama-3.1-70B-Instruct-AQLM-PV-2Bit-1x16

Text Generation • 11B • Updated Sep 17, 2024 • 32 • 45

ISTA-DASLab/Meta-Llama-3.1-70B-AQLM-PV-2Bit-1x16

Text Generation • 11B • Updated Sep 14, 2024 • 39 • 18

ISTA-DASLab/Meta-Llama-3-70B-AQLM-PV-1Bit-1x16

Text Generation • 7B • Updated Sep 14, 2024 • 17 • 1

ISTA-DASLab/Meta-Llama-3.1-8B-Instruct-AQLM-PV-2Bit-1x16-hf

Text Generation • 2B • Updated Aug 28, 2024 • 49 • 8

ISTA-DASLab/Mistral-Nemo-Instruct-2407-AQLM-PV-2Bit-1x16-hf

3B • Updated Aug 16, 2024 • 11 • 3

ISTA-DASLab/AQLM-executorch

Updated Aug 12, 2024 • 30 • 18

ISTA-DASLab/Meta-Llama-3.1-8B-Instruct-AQLM-PV-1Bit-1x16-hf

Text Generation • 2B • Updated Aug 9, 2024 • 20 • 1

ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-1Bit-1x16-hf

Text Generation • 2B • Updated Aug 9, 2024 • 15 • 1

ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf

Text Generation • 2B • Updated Aug 9, 2024 • 18 • 3

ISTA-DASLab/Meta-Llama-3.1-8B-Instruct-AQLM-PV-2Bit-2x8-hf

Text Generation • 3B • Updated Aug 9, 2024 • 47 • 2

ISTA-DASLab/Phi-3-mini-4k-instruct-AQLM-PV-2Bit-1x16-hf

Text Generation • 0.7B • Updated Aug 3, 2024 • 16 • 2

ISTA-DASLab/Qwen2-72B-AQLM-PV-1bit-1x16

Text Generation • 12B • Updated Jul 25, 2024 • 5

ISTA-DASLab/Qwen2-72B-AQLM-PV-2bit-1x16

Text Generation • 12B • Updated Jul 25, 2024 • 5

ISTA-DASLab/Qwen2-72B-Instruct-AQLM-PV-2bit-1x16

Text Generation • 12B • Updated Jul 25, 2024 • 10 • 1

ISTA-DASLab/Qwen2-72B-Instruct-AQLM-PV-1bit-1x16

Text Generation • 7B • Updated Jul 25, 2024 • 7 • 1

ISTA-DASLab/Phi-3-medium-4k-instruct-AQLM-PV-1Bit-1x16-hf

Text Generation • 1B • Updated Jul 8, 2024 • 8

ISTA-DASLab/Phi-3-medium-4k-instruct-AQLM-PV-2Bit-1x16-hf

Text Generation • 2B • Updated Jul 8, 2024 • 10

ISTA-DASLab/Meta-Llama-3-8B-AQLM-2Bit-1x16

Text Generation • 2B • Updated Jul 2, 2024 • 29 • 8

ISTA-DASLab/Llama-2-13b-AQLM-2Bit-2x8-hf

Text Generation • 4B • Updated Jun 4, 2024 • 13

ISTA-DASLab/Meta-Llama-3-70B-AQLM-PV-2Bit-1x16

Text Generation • 11B • Updated May 31, 2024 • 7 • 4

ISTA-DASLab/Meta-Llama-3-8B-AQLM-PV-2Bit-1x16

Text Generation • 2B • Updated May 31, 2024 • 17 • 4

ISTA-DASLab/Meta-Llama-3-8B-AQLM-PV-1Bit-1x16

Text Generation • 2B • Updated May 31, 2024 • 16

ISTA-DASLab/Llama-2-7b-AQLM-PV-1Bit-1x16-hf

Text Generation • 0.9B • Updated May 31, 2024 • 20

ISTA-DASLab/Llama-2-70b-AQLM-PV-2Bit-1x16-hf

Text Generation • 9B • Updated May 31, 2024 • 14