Pull Requests intel/auto-round

docs: explain Windows Triton compilation prerequisites

#2432 by Shubham-Padkonde was merged 2026-09-30 12:52

fix: apply debug layer limits to nested configs

#2431 by Shubham-Padkonde was merged 2026-09-30 12:54

Update version to 0.17.0

#2429 by XuehaoSun was merged 2026-09-30 11:46

update README.md

#2428 by wenhuach21 was merged 2026-09-30 05:50

add mxuint

#2425 by wenhuach21 was merged 2026-09-30 06:16

INC integration test bug fix

#2423 by chensuyue was merged 2026-09-30 02:30 0.16.0

fix: honor AR_WORK_SPACE for the AudioCaps dataset cache

#2420 by Shubham-Padkonde was merged 2026-09-30 05:42

fix: return the repaired string from escape_invalid_json_backslashes

#2419 by Shubham-Padkonde was merged 2026-09-30 05:46

Keep the case of the AR_WORK_SPACE path

#2417 by Shubham-Padkonde was merged 2026-09-30 05:44

fix(xpu): make ARK SDPA graph-capture safe for torch.xpu.XPUGraph

#2416 by luoyu-intel was merged 2026-09-24 13:47 0.16.0

bug fix: prune static kv/attention granularity keys when dtype not set

#2415 by yiliu30 was merged 2026-09-24 08:48 0.16.0

fix: materialize checkpoint-backed cpu buffers

#2412 by n1ck-guo was merged 2026-09-23 23:43 0.16.0

bug fix: layer_config mismatch due to transformers rename; fix model free stream mode detection

#2411 by xin3he was merged 2026-09-24 07:13 0.16.0

enhance attention module with original implementation retrieval…

#2408 by xin3he was merged 2026-09-24 08:00 0.16.0

Revert "refactor: decouple datatype quantization from algorithms

#2406 by n1ck-guo was merged 2026-09-22 05:03 0.16.0

fix: avoid excessive memory during calibration dataset casting

#2405 by changwangss was merged 2026-09-22 05:31 0.16.0

fix: update tensor summary creation to directly use tensors_to_restor…

#2401 by xin3he was merged 2026-09-22 01:56 0.16.0

bug fix: enhance max_scale handling in qdq method and add unit tests for…

#2398 by xin3he was closed 2026-09-21 05:07 0.16.0

fix: update get_predefined_ignore_layers to include shared_expert_gat…

#2397 by xin3he was merged 2026-09-22 01:56 0.16.0

Honour the padding mask in SignRoundV2's plain loss

#2395 by Shubham-Padkonde was merged 2026-09-21 06:58 0.16.0

Move the zero point to CPU for asymmetric layers too

#2394 by Shubham-Padkonde was merged 2026-09-21 06:54 0.16.0

Apply autocast only when mixed precision is enabled

#2393 by Shubham-Padkonde was merged 2026-09-21 06:52 0.16.0

fix: fake format has no FP32 tensor restoration

#2392 by xin3he was merged 2026-09-21 02:34 0.16.0

fix model_free saving with single shard and MXFP fake format evaluation

#2391 by xin3he was merged 2026-09-21 02:35 0.16.0

Fix CWE-22 (path traversal) in checkpoint loading issues

#2389 by lvliang-intel was merged 2026-09-24 01:17 0.16.0

fix: update import to include get_model_path for model retrieval

#2388 by xin3he was merged 2026-09-20 06:49 0.16.0

Cast float32 weights to the export dtype when saving

#2385 by Shubham-Padkonde was merged 2026-09-21 02:52 0.16.0

fix:reduce memory usage when loading native fused MoE checkpoints

#2382 by n1ck-guo was merged 2026-09-20 02:39 0.16.0

fix: share NVFP4 global scales for Wan QKV projections bug

#2379 by changwangss was merged 2026-09-18 07:29 0.16.0

patch triangular_solve for Qwen3.8 model for hpu

#2377 by lkk12014402 was merged 2026-09-18 02:48 0.16.0