intel/auto-round

Pull Requests Commits

Merge branch 'main' into lvl/refine_device_class

lvliang-intel committed 22 days ago

Verified 13e99f25

fix: preserve declared FP32 tensors during model dtype conversion (#2359)

changwangss committed 22 days ago

Verified b33eedc9

fix: support list inputs in diffusion tuning cache (#2346)

changwangss committed 23 days ago

Verified c53611fb

fix: update key cache access for compatibility with newer DynamicCache implementation (#2348)

chensuyue committed 23 days ago

Verified f331bb02

fix: reload Diffusers blocks from component checkpoints (#2353)

changwangss committed 24 days ago

Verified 6a8d95f4

fix qwen35 regression (#2352)

wenhuach21 committed 25 days ago

Verified 141e4c99

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 26 days ago

d482c423

Merge branch 'main' into lvl/refine_device_class

lvliang-intel committed 26 days ago

Verified 9569be78

feat: implement resume functionality for model-free compression (#2330)

xin3he committed 26 days ago

Verified 9e2650f4

enhance device manager

lvliang-intel committed 26 days ago

dbc260e7

Update README.md (#2343)

wenhuach21 committed 26 days ago

Verified 51003909

Keep the original checkpoint key names and fix Qwen4 vLLM inference (#2327)

wenhuach21 committed 26 days ago

Verified aba0abdd

feat: add opt-in diffusion tuning cache prefetch (#2340)

changwangss committed 27 days ago

Verified 585d2065

fix: recreate calibrator for secondary diffusion transformers (#2335)

changwangss committed 27 days ago

Verified cea5abd7

fix: preserve layer config for secondary diffusion transformers (#2337)

changwangss committed 27 days ago

Verified c78c11a6

Improve the low_cpu_mem_usage usage in the doc (#2278)

hshen14 committed 27 days ago

Verified 32369a69

XPU oneDNN: bind matmul execution to live SYCL queue (graph-capture safe) (#2280)

Copilot committed 27 days ago

Verified 79516ff3

feat: add transformers checkpoint conversion mapping support for missing tensors (#2328)

xin3he committed 28 days ago

Verified 1139c323

feat: add support for WOQ fake quantization in model-free mode and update… (#2329)

xin3he committed 28 days ago

Verified bdc60475

refactor: reorganize tensor utility functions and enhance split_fused_expert_tensors for special cases (#2320)

xin3he committed 28 days ago

Verified c18bf770

fix nemoron gate inference issue (#2325)

wenhuach21 committed 28 days ago

Verified 0ea7c93c

fix: pin Hugging Face snapshots for AutoScheme offload reloads (#2318)

n1ck-guo committed 28 days ago

Verified 34c385ad

[high risk]Speedup 2.5-6X moe tuning and pin ngram to cpu (#2303)

wenhuach21 committed 29 days ago

Verified 678f8f5f

fix: update artifact name format for ark wheel download (#2321)

chensuyue committed 29 days ago

Verified b1738032

Implement AI-Powered CI Failure Analysis and Fix Recommendations (#2277)

chensuyue committed 29 days ago

Verified 18486c39

reduce cuda ut runing time (#2266)

n1ck-guo committed 29 days ago

Verified bdb0d31f

support model_type == "inkling_mm_model" (#2214)

xin3he committed 30 days ago

Verified de801f9f

fix: defer packing for multi-transformer diffusion (#2314)

changwangss committed 30 days ago

Verified b4dc0cc7

fix: update quantization configuration handling in FakeFormat and related tests (#2311)

xin3he committed 30 days ago

Verified 777c4ea7

Optimize diffusion calibration step sampling (#2265)

changwangss committed 30 days ago

Verified ce90add6

Older