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
c4e61133fbb5587e0cf8972ce32ffac4e37fa739
vllm-omni
/
vllm_omni
/
distributed
/
omni_connectors
T
History
tzhouam
and
Claude Fable 5.1
66319ed159
[Edge][WP8] Sample the chunk hop put->get latency before the shm get removes the lock file
...
Co-Authored-By: Claude Fable 5.1 <
noreply@anthropic.com
>
2026-09-09 15:25:43 +08:00
..
connectors
[Edge][WP7] Add CudaIpcConnector (CUDA IPC for device tensor leaves over shm control plane)
2026-09-09 14:41:33 +08:00
transfer_adapter
[Edge][WP8] Sample the chunk hop put->get latency before the shm get removes the lock file
2026-09-09 15:25:43 +08:00
utils
[Refactor][OutputProcessor 2/8]: OmniRequestOutput should inherit RequestOutput and no nested wrap-up (
#5146
)
2026-08-12 22:58:23 +08:00
__init__.py
add moriio transfer engine (
#1742
)
2026-06-10 08:37:33 +08:00
adapter.py
[Model] Preserve MiniCPM-o Talker full attention until capacity (
#6799
)
2026-09-06 22:25:35 +08:00
factory.py
[Edge][WP7] Add CudaIpcConnector (CUDA IPC for device tensor leaves over shm control plane)
2026-09-09 14:41:33 +08:00
kv_transfer_manager.py
[BugFix] Make pure-TP KV receive fallback all-or-nothing across ranks (
#5636
)
2026-08-01 15:43:48 +00:00