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
59ae174bba28730d2e96c66429da42691129dae5
vllm-omni
/
vllm_omni
/
worker
T
History
Zhou Taichang
59ae174bba
[Debug] Debug qwen3 mix modality output empty string (
#431
)
...
Signed-off-by: tzhouam <
tzhouam@connect.ust.hk
>
2025-12-30 15:32:15 +08:00
..
npu
[Bugfix][NPU] Add _model_forward for ModelRunner (
#505
)
2025-12-28 04:09:34 +08:00
__init__.py
Initial vLLM-omni repository structure
2025-09-11 14:32:51 +08:00
gpu_ar_model_runner.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
gpu_ar_worker.py
[Core] Supports stage abstraction in the diffusion model (
#391
)
2025-12-27 01:59:33 +13:00
gpu_generation_model_runner.py
model forward call logic fixes (
#495
)
2025-12-27 14:22:07 +00:00
gpu_generation_worker.py
[Rebase] Rebase to vllm 0.12.0 (
#335
)
2025-12-19 16:42:02 +08:00
gpu_model_runner.py
[Debug] Debug qwen3 mix modality output empty string (
#431
)
2025-12-30 15:32:15 +08:00