intel/auto-round

Pull Requests Commits

Add fuzz tests for parsing and path safety in auto_round

chensuyue committed 13 hours ago

076202fe

update cli and simplify --help (#2530)

n1ck-guo committed 5 days ago

Verified aca358a1

Enhance AI analysis and PR comment handling (#2538)

chensuyue committed 5 days ago

Verified c1d97369

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

xin3he committed 5 days ago

Verified 9ffe65f7

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

changwangss committed 6 days ago

Verified 3e186445

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

wenhuach21 committed 6 days ago

Verified 3f86dea7

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

chensuyue committed 6 days ago

Verified e4353de0

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

xin3he committed 7 days ago

Verified 91a9bbfc

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

xin3he committed 7 days ago

Verified e2e3f17f

Reset Inductor Pool After SGLang Shutdown (#2536)

XuehaoSun committed 7 days ago

Verified afac833e

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

changwangss committed 7 days ago

Verified 76a114e5

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

xin3he committed 8 days ago

Verified 512872d0

remove CI trigger for cuda nightly (#2541)

chensuyue committed 8 days ago

Verified 90cbfe45

refactor: extract extensible shared smoothing engine (#2452)

changwangss committed 9 days ago

Verified 9cc08ca7

feat: export SVDQuant NVFP4 checkpoints for vLLM-Omni (#2445)

changwangss committed 9 days ago

Verified 7c0aed07

feat: enhance FP32 tensor handling in mixed-precision checkpoints and… (#2519)

xin3he committed 9 days ago

Verified 1d623e2a

feat: W4A8 ARK XPU MoE kernel (int4 weight / int8 compute) with prefill + decode (#2143)

Copilot committed 12 days ago

Verified 80b5f874

enhance: add source config preservation in save_model and related tests (#2522)

xin3he committed 12 days ago

Verified 710dcaef

feat: multi-GPU quantization improvements -- batched device-local sea… (#2357)

avtc committed 13 days ago

Verified a7656a27

enhance model_free functionality with strict parameter validation (#2520)

xin3he committed 13 days ago

Verified 95eccea1

update lfq acc data (#2529)

wenhuach21 committed 13 days ago

Verified 5ce470f4

fix lfq loss (#2527)

wenhuach21 committed 14 days ago

Verified 071829b0

fix: allocate calibration samples correctly when mixing datasets (#2526)

unknownhackerworld committed 14 days ago

Verified 436fa5a3

Fix ruff SIM117 in eval CLI test (#2523)

XuehaoSun committed 15 days ago

Verified c2dbac79

fix: keep escapes and quantified dots in to_standard_regex (#2418)

Shubham-Padkonde committed 15 days ago

Verified fd28e78b

Trigger CI test for RC branch (#2513)

chensuyue committed 15 days ago

Verified de2f5f06

Bump to v0.16.1 (#2517)

XuehaoSun committed 16 days ago

Verified cbdec9f3

fix: use spawn start method for vLLM evaluation to avoid CUDA re-initialization error (#2421)

reginaldalfret committed 16 days ago

Verified 234ac7af

fix: preserve calibration dataset on memory errors (#2433)

Shubham-Padkonde committed 16 days ago

Verified fde1f580

feat: support LLMC/ModelOpt/Quark format NVFP4 -> MXFP4 conversion (#2492)

xin3he committed 16 days ago

Verified 7222a20e

Older