Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

IST Austria Distributed Algorithms and Systems Lab

university
https://ist.ac.at/en/research/alistarh-group/
https://github.com/IST-DASLab
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

kwanhee  updated a model about 9 hours ago
ISTA-DASLab/Qwen3.5-397B-A17B-P48NVFP4-MoESQ
kwanhee  updated a model about 9 hours ago
ISTA-DASLab/Qwen3-30B-A3B-P48NVFP4-MoESQ
kwanhee  updated a model about 9 hours ago
ISTA-DASLab/Kimi-K2.5-P48NVFP4-MoESQ
View all activity

Papers

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

Disaggregated Quantization: Specializing LLM Prefill and Decode

View all Papers

Eldar Kurtić's profile picture Denis Kuznedelev's profile picture Ionut Modoranu's profile picture Rush Tabesh's profile picture Eugenia Iofinova's profile picture Dan Alistarh's profile picture Elias Frantar's profile picture Alistarh's profile picture Andrei Panferov's profile picture amir moeini's profile picture Vladimir's profile picture Yozh's profile picture Jiale Chen's profile picture Tommaso Pegolotti's profile picture Vahe's profile picture Michael Helcig's profile picture Max Kleinegger's profile picture Alireza Dadgarnia's profile picture Kwanhee Lee's profile picture
ISTA-DASLab 's papers 16
Submitted by
Andrei Panferov
79

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

ISTA-DASLab IST Austria Distributed Algorithms and Systems Lab
129 2
Submitted by
Alistarh
44

QuEST: Stable Training of LLMs with 1-Bit Weights and Activations

ISTA-DASLab IST Austria Distributed Algorithms and Systems Lab
82 3
1

Scalable Mechanistic Neural Networks

ISTA-DASLab IST Austria Distributed Algorithms and Systems Lab
2
1

MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models

ISTA-DASLab IST Austria Distributed Algorithms and Systems Lab
1.15k
  • Previous
  • 1
  • 2
  • Next
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs