Logo
Explore Help
Sign In
anodyine/vllm-omni
Watch 1
Star 0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
Files
e2796b616847b2be2587e1c2dc0cff13b657f6d0
vllm-omni/vllm_omni/diffusion/offloader
T
History
Hongsheng Liu e2796b6168 [Diffusion] Add loader-owned host-weight plans for DLO
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-08-15 23:32:27 +08:00
..
__init__.py
[Diffusion] Add loader-owned host-weight plans for DLO
2026-08-15 23:32:27 +08:00
base.py
[Diffusion] Add loader-owned host-weight plans for DLO
2026-08-15 23:32:27 +08:00
block_discovery.py
[Feature] Distributed layerwise offload with DP multi-concurrency + mmap weight… (#5397)
2026-07-30 13:35:38 +00:00
distributed_layerwise_backend.py
[Diffusion] Add loader-owned host-weight plans for DLO
2026-08-15 23:32:27 +08:00
layerwise_backend.py
[Diffusion][Quantization] Enable MiniMax-H3 global FP8 with DLO (#5910)
2026-08-15 23:01:26 +08:00
module_collector.py
feat(minimax-h3): enable 2x RTX 4090/5090 with DLO (#5764)
2026-08-06 09:02:29 +08:00
module_residency.py
feat(minimax-h3): enable 2x RTX 4090/5090 with DLO (#5764)
2026-08-06 09:02:29 +08:00
offload_plan.py
[Diffusion] Add loader-owned host-weight plans for DLO
2026-08-15 23:32:27 +08:00
sequential_backend.py
Extend Cosmos3 CPU offloading to component and layerwise paths (#4695)
2026-07-13 09:48:53 +00:00
tensor_utils.py
[Feature] Distributed layerwise offload with DP multi-concurrency + mmap weight… (#5397)
2026-07-30 13:35:38 +00:00
Powered by Gitea Version: 28.1.0 Page: 56ms Template: 4ms
Auto
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API