intel/auto-round

Pull Requests Commits

yiliu30 committed 57 days ago

1c989d90

fix q scale shape

yiliu30 committed 58 days ago

ddc59772

yiliu30 committed 58 days ago

0a2de215

yiliu30 committed 59 days ago

a7b6c33a

yiliu30 committed 60 days ago

cdcc5c4f

yiliu30 committed 60 days ago

2d2c3122

yiliu30 committed 60 days ago

9d09edec

yiliu30 committed 60 days ago

be5d94ed

enable compile for hpu

yiliu30 committed 60 days ago

e9157967

yiliu30 committed 61 days ago

65a467ee

yiliu30 committed 61 days ago

591549b2

Bump into v0.9.0 (#1024)

XuehaoSun committed 64 days ago

Verified 8d8a1cd5

fix incorrect model name (#1035)

wenhuach21 committed 64 days ago

Verified 509ac2c3

optimize vram for gguf and add momentum (#1031)

wenhuach21 committed 64 days ago

Verified 58b3d90a

update gguf alg ext (#1026)

n1ck-guo committed 64 days ago

Verified 81caded3

Reduce mem usage of GPT-OSS (#1013)

yiliu30 committed 64 days ago

Verified 6d3d87d0

Fix the missing temporary name (#1029)

yiliu30 committed 64 days ago

Verified c4d030da

fix bug of lm_head and dispatch model,gguf eval (#1025)

n1ck-guo committed 65 days ago

Verified 2fb3ee1b

disable itrex format first (#998)

WeiweiZhang1 committed 66 days ago

Verified 395602b7

fix cuda ut (#1020)

n1ck-guo committed 66 days ago

Verified 797f476a

dispatch model with real max memory (#1022)

xin3he committed 66 days ago

Verified 255322fb

add num_device check for set_auto_device_map_for_block_with_tuning (#1021)

xin3he committed 66 days ago

Verified a3d422df

Including auto_scheme.default_alg into binary (#1018)

chensuyue committed 66 days ago

Verified 6d03ec89

fix multi cuda ut bug (#1014)

n1ck-guo committed 67 days ago

Verified d00cc855

add ut for gguf alg_ext and update so file (#1012)

n1ck-guo committed 67 days ago

Verified 5c2f1bd7

fix bug (#1011)

wenhuach21 committed 68 days ago

Verified e3f96105

Minor refactor for LLMC (#993)

yiliu30 committed 68 days ago

Verified 6af724a5

add device list to clear memory (#1009)

wenhuach21 committed 68 days ago

Verified 1d02da16

Fix param missing bug (#1008)

mengniwang95 committed 68 days ago

Verified 7f9fa0ee

fix cuda CI (#1010)

Kaihui-intel committed 68 days ago

Verified b7ef006b

Older