intel/auto-round

Pull Requests Commits
format
yiliu30 committed 47 days ago
e5044b40
fix
yiliu30 committed 47 days ago
efd3b1dc
update
yiliu30 committed 47 days ago
7b986e3a
update
yiliu30 committed 47 days ago
ebe9d790
update
yiliu30 committed 47 days ago
01665c90
add gene
yiliu30 committed 47 days ago
3d21a74f
update
yiliu30 committed 47 days ago
c9dbac02
update
yiliu30 committed 47 days ago
84f3dbe8
fix
yiliu30 committed 47 days ago
5f799b8d
add readme
yiliu30 committed 47 days ago
edd3e9e6
fix
yiliu30 committed 47 days ago
bb4d90c2
fix
yiliu30 committed 47 days ago
fbc04aeb
fix cuda ut (#1020)
n1ck-guo committed 47 days ago
Verified 797f476a
dispatch model with real max memory (#1022)
xin3he committed 47 days ago
Verified 255322fb
add num_device check for set_auto_device_map_for_block_with_tuning (#1021)
xin3he committed 47 days ago
Verified a3d422df
fix moe mxfp8
yiliu30 committed 47 days ago
493f2df2
Including auto_scheme.default_alg into binary (#1018)
chensuyue committed 47 days ago
Verified 6d03ec89
fix multi cuda ut bug (#1014)
n1ck-guo committed 48 days ago
Verified d00cc855
add mxfp4-mxfp8-moe
yiliu30 committed 48 days ago
7eb99749
add ut for gguf alg_ext and update so file (#1012)
n1ck-guo committed 48 days ago
Verified 5c2f1bd7
fix bug (#1011)
wenhuach21 committed 49 days ago
Verified e3f96105
Minor refactor for LLMC (#993)
yiliu30 committed 49 days ago
Verified 6af724a5
clean code
yiliu30 committed 49 days ago
347d6800
update example
yiliu30 committed 49 days ago
218f5645
add device list to clear memory (#1009)
wenhuach21 committed 49 days ago
Verified 1d02da16
fix skip layers
yiliu30 committed 49 days ago
936ec4e6
add mxfp4 moe
yiliu30 committed 49 days ago
284c41e1
Fix param missing bug (#1008)
mengniwang95 committed 49 days ago
Verified 7f9fa0ee
fix qwen mxfp4
yiliu30 committed 49 days ago
553529ae
fix cuda CI (#1010)
Kaihui-intel committed 49 days ago
Verified b7ef006b
Terms Of Use Privacy Policy Refund Policy Impressum