auto-round
Support ByteDance-Seed/BAGEL-7B-MoT quantization in w4a16 format
#1633
Merged

Support ByteDance-Seed/BAGEL-7B-MoT quantization in w4a16 format #1633

lvliang-intel merged 37 commits into main from lvl/support_bagel_mot
lvliang-intel
lvliang-intel lvliang-intel requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 122 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-03-27
lvliang-intel
wenhuach21
hshen14 hshen14 requested a review from xin3he xin3he 103 days ago
hshen14 hshen14 requested a review from yiliu30 yiliu30 103 days ago
lvliang-intel Support BAGEL quantization
dd92ae04
lvliang-intel update code
14ed1bd3
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
2435fa04
lvliang-intel Update auto_round/utils/bagel_loader.py
7795f1d1
lvliang-intel Update auto_round/utils/model.py
c1bfc7d0
Copilot Fix save_pretrained to use state_dict() instead of named_parameters()
9ac70a94
xin3he remove IPEX related code, doc, and test (#1787)
82c5311a
lvliang-intel Support BAGEL quantization
58d80316
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
2b5df312
lvliang-intel fix typo
f15d897d
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
576e4740
lvliang-intel let pre-commit not change MOT to NOT
595f22da
lvliang-intel lvliang-intel force pushed from 4983fc85 to 595f22da 76 days ago
lvliang-intel Restore auto_round_kernel/version.py deleted during rebase
3bd5343b
lvliang-intel lvliang-intel force pushed from a06ceb61 to 3bd5343b 76 days ago
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
a056682e
lvliang-intel
azure-pipelines
lvliang-intel
azure-pipelines
yiliu30
yiliu30 approved these changes on 2026-05-14
lvliang-intel Update auto_round/utils/bagel_loader.py
a73fa5c1
yiliu30 Fix FP8 CT export metadata for KV cache and attention (#1752)
8bac01dd
chensuyue Enhance ark test workflow (#1805)
4f1a044b
n1ck-guo Fix GGUF-K RTN routing and fake eval dtype normalization (#1807)
641827aa
lvliang-intel Fix mixed-precision accuracy regression when AutoScheme runs with CPU…
b99b1ecb
chensuyue Add Dockerfile with torch installed, enhance image build logic to che…
33a130a0
wenhuach21 set default DYNAMO_CACHE_SIZE_LIMIT to 16 (#1786)
85b46e42
xin3he reduce XPU memory usage in CI (#1812)
1e346fe6
n1ck-guo [refactor] decouple calibaration code (#1765)
bb068956
chensuyue [ARK CI] Enhance auto-round-lib CI test (#1801)
77dc57ac
lvliang-intel Support BAGEL quantization
49dc905a
lvliang-intel Support BAGEL quantization
7b92f143
lvliang-intel add ut
fb89eb82
lvliang-intel Merge branch 'main' into lvl/support_bagel_mot
574450ee
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
1567f9ad
lvliang-intel
lvliang-intel
azure-pipelines
lvliang-intel Support BAGEL quantization
ec7936e3
lvliang-intel Support BAGEL quantization
0d40acdb
n1ck-guo [refactor] decouple calibaration code (#1765)
65eb04c5
lvliang-intel fix ut
4538be3f
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
9e5893ef
lvliang-intel fix pre-commit
2b5ee144
lvliang-intel
azure-pipelines
lvliang-intel
azure-pipelines
lvliang-intel Merge branch 'main' into lvl/support_bagel_mot
06157c14
lvliang-intel
azure-pipelines
lvliang-intel Merge branch 'main' into lvl/support_bagel_mot
e631d4df
lvliang-intel
azure-pipelines
XuehaoSun
azure-pipelines
lvliang-intel lvliang-intel merged 91679a5c into main 70 days ago
lvliang-intel lvliang-intel deleted the lvl/support_bagel_mot branch 70 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone