intel/auto-round

Pull Requests Commits
init
n1ck-guo committed 1 year ago
573b9aca
fix
n1ck-guo committed 1 year ago
03730041
bump to v0.4.5 (#425)
XuehaoSun committed 1 year ago
Verified 096bc196
fix eval trust_remote_code (#424)
n1ck-guo committed 1 year ago
Verified 5c075a9f
fix cuda UT torch_dtype (#423)
WeiweiZhang1 committed 1 year ago
Verified db8088b2
support to export deepseek v3 gguf format (#416)
n1ck-guo committed 1 year ago
Verified 6a49304e
fix evaluation device bug, relate to issue 413 (#419)
n1ck-guo committed 1 year ago
Verified 22315cc5
merge with main
yiliu30 committed 1 year ago
eef8d290
add UT
yiliu30 committed 1 year ago
54e5b575
remove empty line
yiliu30 committed 1 year ago
3bc3b22c
refine llm script
yiliu30 committed 1 year ago
4fa68013
refine llm script
yiliu30 committed 1 year ago
0a795d98
rm global_config
yiliu30 committed 1 year ago
c39fa40f
remove global_config
yiliu30 committed 1 year ago
80bd1678
revert unrelated change
yiliu30 committed 1 year ago
b4f5acae
clean code
yiliu30 committed 1 year ago
76009f2f
enable backup pile dataset loading (#417)
WeiweiZhang1 committed 1 year ago
Verified a9b5ae4f
support bf16 inference (#420)
wenhuach21 committed 1 year ago
Verified 29c5119f
support naive multi-card tuning (#415)
wenhuach21 committed 1 year ago
Verified 09f1ab49
speedup packing stage for autogptq and autoawq format (#407)
wenhuach21 committed 1 year ago
Verified 937d0198
fix log bug and device "auto" bug (#409)
n1ck-guo committed 1 year ago
Verified ba5975c8
update format readme (#411)
wenhuach21 committed 1 year ago
Verified a40ce88d
clean code
Yi4Liu committed 1 year ago
d752280d
support to export gguf q4_0 and q4_1 format (#393)
n1ck-guo committed 1 year ago
Verified 86767b0f
tune bf16 to fp8 scale
Yi4Liu committed 1 year ago
14203d64
support awq with qbits, only support sym (#402)
wenhuach21 committed 1 year ago
Verified ba2426cd
llm_layer_config_bugfix (#406)
WeiweiZhang1 committed 1 year ago
Verified 7714796a
add pc
Yi4Liu committed 1 year ago
997a43b7
support for deepseek vl2 (#401)
n1ck-guo committed 1 year ago
Verified bf8d68d1
fix dtype converting issue (#403)
wenhuach21 committed 1 year ago
Verified 6ac7a2b2
Terms Of Use Privacy Policy Refund Policy Impressum