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
ff0a76e31cbdb1f3bc5b0cb11f75ee63d5dbd3ca
vllm-omni
/
vllm_omni
/
platforms
/
npu
/
worker
T
History
rein yang
and
Sy03
ad3a162eb8
[perf] Minicpm o4.5 optimization (
#5228
)
...
Signed-off-by: R2-Y <
ruiruyang2@gmail.com
> Co-authored-by: Sy03 <
1370724210@qq.com
>
2026-07-24 17:20:39 +08:00
..
__init__.py
[Hardware] Support platforms and plugin system (
#774
)
2026-01-28 22:12:52 +08:00
base.py
[Hardware][Ascend] Adapt Qwen3 TTS for 310P (
#4283
)
2026-06-12 09:39:21 +00:00
npu_ar_model_runner.py
[perf] Minicpm o4.5 optimization (
#5228
)
2026-07-24 17:20:39 +08:00
npu_ar_worker.py
[Refactor] Unify torch profiler for omni and diffusion models (
#2099
)
2026-03-24 15:25:52 +08:00
npu_generation_model_runner.py
[Bugfix] Skip non-positive scheduled token spans in omni stage runners (
#5269
)
2026-07-22 16:01:45 +00:00
npu_generation_worker.py
[Refactor] Unify torch profiler for omni and diffusion models (
#2099
)
2026-03-24 15:25:52 +08:00
npu_model_runner.py
[NPU] Upgrade to v0.24.0 (
#4848
)
2026-07-03 07:01:25 +00:00