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
a964efc55b6c36ed6a9214a8cf4bb131f368183d
vllm-omni
/
vllm_omni
/
model_executor
T
History
NATURE
49977ce7a3
[Perf] release unused Code2Wav stream caches (
#6100
)
...
Signed-off-by: natureofnature <
wzliu@connect.hku.hk
>
2026-08-12 18:43:40 +08:00
..
layers
Add NPU support for OmniMRotaryEmbedding (
#3609
)
2026-06-18 16:58:40 +08:00
model_loader
[Fix]Ensure HuggingFace downloads complete before initialization. (
#1213
)
2026-02-10 16:05:12 +08:00
models
[Perf] release unused Code2Wav stream caches (
#6100
)
2026-08-12 18:43:40 +08:00
stage_input_processors
[WIP][Bugfix][MiniCPM-o] Fix Full duplex bugs for minicpm-challenge (
#5496
)
2026-07-28 15:59:26 +08:00
__init__.py
update ar_dit_test
2025-09-28 21:58:48 +08:00
custom_process_mixin.py
[Core] customize process between stages, remove the need of "request_ids" in model forward, rebase to 0.12.0 (
#458
)
2025-12-24 13:26:33 +00:00