intel/auto-round

Pull Requests Commits

docs: clarify filter_quantization_config comment

n1ck-guo committed 2 days ago

08decd8e

fix: always save key AutoRound hyper-parameters to config.json

n1ck-guo committed 2 days ago

ef566fc7

refine export and format code and provide unify api (#2540)

n1ck-guo committed 2 days ago

Verified caf6388d

fix: default AWQ to optimized RTN (disable_opt_rtn=False) (#2572)

WeiweiZhang1 committed 2 days ago

Verified 6c6566f8

fix: support Nemotron-H Omni without mamba_ssm (#2537)

urakozz committed 2 days ago

Verified e73b38a4

fix: support Diffusers weight filenames in low-memory mode (#2580)

changwangss committed 3 days ago

Verified 9c17113a

[High Risk] Support Tensor Parallelism and LoRA, Optimize FP4 MoE Tuning Speed, and Refactor the Code (#2567)

wenhuach21 committed 3 days ago

Verified 5db10829

support for recipes such as ar-best ar-light (#2547)

n1ck-guo committed 4 days ago

Verified 8869842f

feat: data-parallel block tuning via --data_parallel (#2351)

avtc committed 4 days ago

Verified 6c824f74

chore: update CI to PyTorch 2.15 (#2570)

XuehaoSun committed 5 days ago

Verified 853b2641

Record AutoRound hyper-parameters in llm-compressor quantization_config (#2528)

Cross2pro committed 5 days ago

Verified 4ae46af8

docs: add calibration dataset study (#2557)

ZaneMark committed 5 days ago

Verified 07a6e40a

[Research Feature]add naive qat/qad (#2548)

wenhuach21 committed 6 days ago

Verified 57b8648d

support AWQ sample control and optimize AWQ+ARV2 for INT WOQ (#2484)

WeiweiZhang1 committed 8 days ago

Verified 98ad5bbc

fix: preserve Z-Image text encoder export layout (#2559)

changwangss committed 8 days ago

Verified fe68946d

[Bug fix] Release offload temp-file mmap to fix cleanup issue (#2487)

lvliang-intel committed 9 days ago

Verified e1ab33b8

Reset context singletons between tests (#2390)

Shubham-Padkonde committed 9 days ago

Verified d2a25f1b

update cli and simplify --help (#2530)

n1ck-guo committed 9 days ago

Verified aca358a1

Enhance AI analysis and PR comment handling (#2538)

chensuyue committed 9 days ago

Verified c1d97369

[Bug fix]: test/test_mlx/test_mlx_format.py failed on Mac OS (#2554)

xin3he committed 9 days ago

Verified 9ffe65f7

Fix native AutoRound INT4 packing with FP8 layer overrides (#2543)

changwangss committed 9 days ago

Verified 3e186445

Prefetch next batch to CUDA for SignRound v1/v2 under low_gpu_mem_usage (#2549)

wenhuach21 committed 10 days ago

Verified 3f86dea7

Update stale issue and PR handling to 60 days of inactivity (#2553)

chensuyue committed 10 days ago

Verified e4353de0

feat: Add NVFP4_E5M3_GS scheme with global scale support (#2531)

xin3he committed 11 days ago

Verified 91a9bbfc

refactor: Simplify vllm evaluation by setting multiprocessing method directly (#2534)

xin3he committed 11 days ago

Verified e2e3f17f

Reset Inductor Pool After SGLang Shutdown (#2536)

XuehaoSun committed 11 days ago

Verified afac833e

Skip zero-point round-trip with compressed-tensors 0.20.0 (#2544)

changwangss committed 11 days ago

Verified 76a114e5

fix: update scale handling in QuantizedKVParameterCache to use amax of all batches (#2533)

xin3he committed 11 days ago

Verified 512872d0

remove CI trigger for cuda nightly (#2541)

chensuyue committed 12 days ago

Verified 90cbfe45

refactor: extract extensible shared smoothing engine (#2452)

changwangss committed 13 days ago

Verified 9cc08ca7

Older