Skip to content

PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度

Commits on main

Tensor reshape bugfix (#364)
WeiweiZhang1 committed 1 year ago
3ec66bd
fix awq exporting (#358)
Wenhua Cheng committed 1 year ago
ca9e655
174b7cc
Simulated W4Afp8 Quantization (#331)
Wenhua Cheng committed 1 year ago
a98175f
delete llm example and refine readme (#354)
Wenhua Cheng committed 1 year ago
715cd8a
Update docker user and remove baseline UT (#347)
Sun, Xuehao committed 1 year ago
1cb3121
bump version into v0.4.1 (#350)
Sun, Xuehao committed 1 year ago
5030896
triton backend requires< 3.0 (#348)
Wenhua Cheng committed 1 year ago
5c4a908
API use sym as default (#349)
Wenhua Cheng committed 1 year ago
f0546d3
enhance installation check (#346)
Yi Liu committed 1 year ago
96443a9
[VLM]fix bs and grad reset (#344)
Heng Guo committed 1 year ago
28bbf40
[HPU]Enhance numba check (#345)
Yi Liu committed 1 year ago
61e04a8
a7fcb51
fix typo (#342)
Wenhua Cheng committed 1 year ago
9087998
bump version into v0.4 (#341)
Sun, Xuehao committed 1 year ago
b20bff0
refine mllm API and add help info (#334)
Heng Guo committed 1 year ago
22ce956
add cogvlm recipe and refine readme (#340)
WeiweiZhang1 committed 1 year ago
8021793
add qwen2.5 recipe and refine readme (#338)
WeiweiZhang1 committed 1 year ago
e1d820f
cogvlm doc (#339)
Heng Guo committed 1 year ago
7a28ab3
refine mllm docs (#336)
WeiweiZhang1 committed 1 year ago
182dd3f
80988bb
fix model_dtype issue and reformat mllm code (#335)
Wenhua Cheng committed 1 year ago
fcaaac9
58c11fa
56e3400
Increase unit test timeout to 120 minutes (#330)
Sun, Xuehao committed 1 year ago
8d0e89d
debcf83
set default mllm dataset (#327)
Heng Guo committed 2 years ago
ab0a477
Add cpu only version (#315)
Sun, Xuehao committed 2 years ago
0ddcd22