0.17.0

Issues

• [Bug]: kv cache potential bugs

  bughigh priority
  intel/auto-round#2504 · Filter by author wenhuach21 opened on Oct 15, 2026 · 0.17.0
  3

  

• [Feature]: Support FP/INT W4A4 recipe

  intel/auto-round#2009 · Filter by author chensuyue opened on Jul 7, 2026 · 0.17.0
  1

  

• [Feature]: refine lm-head quantization

  enhancement
  intel/auto-round#2176 · Filter by author wenhuach21 opened on Aug 18, 2026 · 0.17.0
  

• [Feature]: support and eval H-Scale: Hessian-Guided Scale Refinement for NVFP4 Sub-Byte LLM Inference

  enhancement
  intel/auto-round#2262 · Filter by author wenhuach21 opened on Aug 31, 2026 · 0.17.0
  

• [Feature]: support and eval VSRAQ

  enhancementStale
  intel/auto-round#2008 · Filter by author wenhuach21 opened on Jul 7, 2026 · 0.17.0
  1

  

• [Feature]: auto-scheme shared_layers supports vllm pattern as default

  enhancementStale
  intel/auto-round#2183 · Filter by author wenhuach21 opened on Aug 18, 2026 · 0.17.0
  1

  

• [Feature]: support FP8+WOQ mix datatypes inference in transformers and vllm

  enhancement
  intel/auto-round#2225 · Filter by author wenhuach21 opened on Aug 25, 2026 · 0.17.0
  

• [Bug]: dump auto-round key hype-parameters to conifg.json

  bugStale
  intel/auto-round#2154 · Filter by author wenhuach21 opened on Aug 13, 2026 · 0.17.0
  1

  

• [Bug]: unexpected enable_quant_input: false in config.json for FP8_BLOCK

  bugStale
  intel/auto-round#2224 · Filter by author wenhuach21 opened on Aug 25, 2026 · 0.17.0
  1

  

• [Model]: TR-HASH MoE with stacked 3D expert weights

  Model Support
  intel/auto-round#2211 · Filter by author Complexity-ML opened on Aug 21, 2026 · 0.17.0
  

• Create default mixed calibration dataset

  high priority
  Task

  intel/auto-round#2071 · Filter by author chensuyue opened on Jul 21, 2026 · 0.17.0
  5

  

• Add a CI check to prevent coverage regressions in pull requests

  Task

  intel/auto-round#2347 · Filter by author chensuyue opened on Sep 11, 2026 · 0.17.0
  3

  

• [Bug]: imbalanced memory usages across cards

  bug
  intel/auto-round#2254 · Filter by author wenhuach21 opened on Aug 28, 2026 · 0.17.0
  2

  

• [Feature]: svdquant supports llm and other schemes(W2A16)

  enhancement
  intel/auto-round#2218 · Filter by author wenhuach21 opened on Aug 24, 2026 · 0.17.0
  

• [Feature]: mxfp4 dual-scale investigate

  intel/auto-round#2199 · Filter by author changwangss opened on Aug 20, 2026 · 0.17.0
  

• [Feature]: refine hardmard code

  enhancement
  intel/auto-round#2036 · Filter by author wenhuach21 opened on Jul 9, 2026 · 0.17.0
  2

  

• Refine device operations into a unified DeviceManager and ARDevice abstraction

  Unread
  intel/auto-round#2344·lvliang-intel opened Sep 11, 2026 · Updated Nov 5, 2026
  17

• [Feature]: Refine device operations into a unified class to simplify support for new devices

  enhancement
  intel/auto-round#1788 · Filter by author wenhuach21 opened on May 8, 2026 · 0.17.0
  

• [Feature]: the ram usage of AutoScheme needs further optimizaiton

  enhancement
  intel/auto-round#1697 · Filter by author wenhuach21 opened on Apr 17, 2026 · 0.17.0
  

• [Feature]: refine export code to provide unified interface for pack_layer and save_quantized_as_format

  enhancementhigh priority
  intel/auto-round#1789 · Filter by author wenhuach21 opened on May 8, 2026 · 0.17.0
  1

  

• [Feature]: Introduce built-in ar, ar-light, and ar-best recipes for each quantization scheme

  enhancementhigh priority
  intel/auto-round#1940 · Filter by author wenhuach21 opened on Jun 22, 2026 · 0.17.0
  1

  

• [Feature]: refine architecture code

  enhancement
  intel/auto-round#2126 · Filter by author wenhuach21 opened on Aug 5, 2026 · 0.17.0
  

• [Feature]: support teq algorithm

  enhancementhigh priority
  intel/auto-round#1888 · Filter by author wenhuach21 opened on Jun 4, 2026 · 0.17.0
  

• [Feature]: move diffusion code from signround quantizer

  enhancement
  intel/auto-round#2399 · Filter by author wenhuach21 opened on Sep 21, 2026 · 0.17.0
  1

  

• Enhance AutoScheme

  Task

  intel/auto-round#910 · Filter by author wenhuach21 opened on Oct 17, 2025 · 0.17.0
  1