ryang
|
ffc23ef877
|
[diffusion] feat: generalize layerwise offloader to flux1 (#15633)
|
2025-12-23 22:22:40 +08:00 |
|
ryang
|
575a49dc0e
|
[diffusion] chore: remove default post-denoising dit offload in local mode (#15573)
|
2025-12-22 17:01:35 +08:00 |
|
 ryangandMengxi Li
|
1e58248808
|
[diffusion] multi-platform: add Sage Attention 3 Support for sm 120 (RTX5090) (#15382)
Co-authored-by: Mengxi Li <marcyleemx@gmail.com>
|
2025-12-19 21:27:02 +08:00 |
|
ryang
|
dccf52f9c8
|
[UT for RL] Add UT to cover release/resume memory case for moe model (#8803)
|
2025-09-09 19:25:12 -07:00 |
|
ryang
|
a6ae3af15e
|
Support XiaomiMiMo inference with mtp (#6059)
|
2025-05-22 14:14:49 -07:00 |
|
ryang
|
4322c31e24
|
Support XiaomiMiMo/MiMo model inference (#5921)
|
2025-05-01 07:41:13 -07:00 |
|
 ryangandYuhao Yang
|
bc24205b32
|
Support BNB quantization for llama/mllama (#5038)
Co-authored-by: Yuhao Yang <yyh073@foxmail.com>
|
2025-04-15 18:00:31 -07:00 |
|