This website requires JavaScript.
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
c7a78b382a8d521fb19403a8dd9c65c32c13ce08
vllm-omni
/
docs
/
design
T
History
Hongsheng Liu
284e05c88b
[Core] Support online FP8 with DLO AllGather (
#6279
)
...
Signed-off-by: Hongsheng Liu <
liuhongsheng4@huawei.com
>
2026-08-18 23:48:07 +08:00
..
feature
[Core] Support online FP8 with DLO AllGather (
#6279
)
2026-08-18 23:48:07 +08:00
figures
docs: document distributed layerwise offload compatibility (
#5839
)
2026-08-06 23:21:43 +08:00
module
[Config] Reuse vLLM configs in VllmOmniConfig (
#6050
)
2026-08-18 21:27:58 +08:00
ar_diffusion_pipeline_capability.md
[Core] Add realtime AR-Diffusion tick sessions for LingBot World 2.0 (
#5491
)
2026-08-16 09:11:20 +08:00
architecture_overview.md
[Docs] Split diffusion attention and CPU offload guides (
#6075
)
2026-08-15 14:41:09 +08:00
index.md
[Core] Add realtime AR-Diffusion tick sessions for LingBot World 2.0 (
#5491
)
2026-08-16 09:11:20 +08:00
metrics.md
[Metrics] Add Diffusion Metrics (
#4755
)
2026-08-13 06:59:13 +00:00
qwen3_omni_tts_performance_optimization.md
[Refactor] Remove legacy --stage-configs-path from the serve CLI (
#5647
)
2026-08-03 23:41:52 +08:00