intel/auto-round

Pull Requests Commits

enhance installation check (#346)

yiliu30 committed 1 year ago

Verified 96443a93

[VLM]fix bs and grad reset (#344)

n1ck-guo committed 1 year ago

Verified 28bbf407

[HPU]Enhance numba check (#345)

yiliu30 committed 1 year ago

Verified 61e04a8e

vllm/llama-vision llava calibration infinite loop fix (#343)

WeiweiZhang1 committed 1 year ago

Verified a7fcb51b

fix typo (#342)

wenhuach21 committed 1 year ago

Verified 90879985

bump version into v0.4 (#341)

XuehaoSun committed 1 year ago

Verified b20bff09

refine mllm API and add help info (#334)

n1ck-guo committed 1 year ago

Verified 22ce956d

add cogvlm recipe and refine readme (#340)

WeiweiZhang1 committed 1 year ago

Verified 80217936

add qwen2.5 recipe and refine readme (#338)

WeiweiZhang1 committed 1 year ago

Verified e1d820fe

cogvlm doc (#339)

n1ck-guo committed 1 year ago

Verified 7a28ab3d

refine mllm docs (#336)

WeiweiZhang1 committed 1 year ago

Verified 182dd3fb

exclude markdown files from unit test pipelines (#337)

XuehaoSun committed 1 year ago

Verified 80988bb5

fix model_dtype issue and reformat mllm code (#335)

wenhuach21 committed 1 year ago

Verified fcaaac91

fix eval_bs in fake format and reset auto-gptq exporting max_shard_size (#332)

wenhuach21 committed 1 year ago

Verified 8fb95526

add tips and tricks for llm&mllm quantization (#333)

wenhuach21 committed 1 year ago

Verified 58c11faf

fix mllm dataset config bug and add gptq cuda backend (#329)

wenhuach21 committed 1 year ago

Verified 56e34003

Increase unit test timeout to 120 minutes (#330)

XuehaoSun committed 1 year ago

Verified 8d0e89d7

fix the bug of test model support for test-only (#328)

n1ck-guo committed 1 year ago

Verified debcf830

fix fp_layers issue and force to FP16 on cuda for autoround format inference (#326)

wenhuach21 committed 1 year ago

Verified 459aab03

set default mllm dataset (#327)

n1ck-guo committed 1 year ago

Verified ab0a477e

Add cpu only version (#315)

XuehaoSun committed 1 year ago

Verified 0ddcd22b

new mllm eval (#317)

n1ck-guo committed 1 year ago

Verified ee816b39

fix merge error (#325)

wenhuach21 committed 1 year ago

Verified dadb95ad

add pile calib, rename quant_block_list to to_quant_block_names (#322)

WeiweiZhang1 committed 1 year ago

Verified d493572f

add warning for no exllamav2 kernel (#324)

wenhuach21 committed 1 year ago

Verified f2ccd6ac

fix multiple device bug (#321)

wenhuach21 committed 1 year ago

Verified 8918df20

fix eval device issue (#319)

wenhuach21 committed 1 year ago

Verified 6aa3d274

update the hpu check (#318)

yiliu30 committed 1 year ago

Verified e1791cd4

fix merge error (#316)

n1ck-guo committed 1 year ago

Verified 606a5c35

add torch compile arg (#314)

wenhuach21 committed 1 year ago

Verified 8a9eed0b

Newer Older