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
009b80d686febcf683fdbc2bcdf3ad752884641e
vllm-omni
/
vllm_omni
/
platforms
T
History
psv666
and
Claude Opus 5
009b80d686
[Bugfix][MiniCPM-o] Wire the duplex sampling hook into the NPU AR model runner (
#5895
)
...
Signed-off-by: psv666 <
2693925048@qq.com
> Co-authored-by: Claude Opus 5 <
noreply@anthropic.com
>
2026-08-07 22:38:45 +08:00
..
cuda
[Attention] Add trtllm diffusion attention backend with Skip-Softmax (
#5283
)
2026-07-27 22:48:11 +08:00
musa
[Refactor] Migrate Legacy Stage Configs to the Pipeline Registry (
#5031
)
2026-07-18 09:34:33 +00:00
npu
[Bugfix][MiniCPM-o] Wire the duplex sampling hook into the NPU AR model runner (
#5895
)
2026-08-07 22:38:45 +08:00
rocm
[Config] Read stage metadata from VllmOmniConfig (
#5343
)
2026-07-27 22:44:06 +08:00
xpu
[Bugfix][XPU] Fix free-memory abort and num_speculative_steps crash on XPU (
#5330
)
2026-07-23 17:17:00 +00:00
__init__.py
[Rebase] Rebase to vllm v0.24.0 (
#4709
)
2026-06-30 19:41:06 +08:00
interface.py
[NPU][HunyuanImage3] Adapt diffusion FusedMoE for vLLM >= 0.24.0 (
#5167
)
2026-07-27 22:41:34 +08:00