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
76e257b0f31d0a01750c0057468ac9d1b3cece86
vllm-omni/vllm_omni/diffusion/offloader
T
History
Hongsheng Liu 76e257b0f3 [Diffusion] Address rank-local mmap review feedback
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-08-14 17:12:05 +08:00
..
__init__.py
feat(minimax-h3): enable 2x RTX 4090/5090 with DLO (#5764)
2026-08-06 09:02:29 +08:00
base.py
[Diffusion] Add rank-local mmap storage for DLO
2026-08-14 14:38:06 +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] Address rank-local mmap review feedback
2026-08-14 17:12:05 +08:00
layerwise_backend.py
[Refactor] Let diffusion pipelines declare offloadable modules via SupportsModuleOffload (#2427)
2026-04-23 04:23:00 +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] Address rank-local mmap review feedback
2026-08-14 17:12:05 +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: 48ms Template: 1ms
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