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
c4f859bf56ef294e0e70b7ea6befdfc5b3f0880b
vllm-omni
/
tests
/
dfx
T
History
Yueqian Lin
c4f859bf56
[CI] Harden Qwen3-TTS perf nightly: enable Base voice_clone, add c=64/128, 2-GPU split (
#3491
)
...
Signed-off-by: Yueqian Lin <
linyueqian@outlook.com
>
2026-05-14 14:26:59 +08:00
..
perf
[CI] Harden Qwen3-TTS perf nightly: enable Base voice_clone, add c=64/128, 2-GPU split (
#3491
)
2026-05-14 14:26:59 +08:00
reliability
[Refactor] Replace and ban a few torch.cuda functions in favor of torch.accelerator replacements. (
#3365
)
2026-05-07 23:23:59 +08:00
stability
[Test] Add stability tests for HunyuanImage-3-Instruct (
#3504
)
2026-05-14 10:47:14 +08:00
conftest.py
[Bugfix] Fix the issue where the qwen3-omni model long-term stability test sometimes gets stuck without sending requests. (
#3468
)
2026-05-13 09:15:20 +08:00