-
Notifications
You must be signed in to change notification settings - Fork 1.3k
Pull requests: vllm-project/vllm-omni
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Feature][Diffusion] Enable BOOGU Image SP2 with 1.67x E2E Speedup
#5516
opened Jul 28, 2026 by
Xenoryn
Loading…
[Kernel] Add typed SAGE for TRTLLM_ATTN
#5509
opened Jul 28, 2026 by
lishunyang12
Collaborator
Loading…
[Model] Add native SANA-Video 2B T2V and I2V support
#5508
opened Jul 28, 2026 by
napleon-liu
Contributor
•
Draft
[CI] [non-CUDA] [ROCm] Fix
get_diffusion_attn_backend_cls() got an unexpected keyword argument 'allow_trtllm_default'
#5505
opened Jul 28, 2026 by
tjtanaa
Member
Loading…
[Perf] Cache RoPE cos/sin tables in code predictor
#5503
opened Jul 28, 2026 by
l-wave
Contributor
Loading…
Add vae-patch-parallel-size and vae-use-tiling for HunyuanImage Benchmark
#5502
opened Jul 28, 2026 by
BLANKETusers
Contributor
Loading…
[CI]Add MiniCPM-o async chunk streaming coverage (vllm-omni 0.25 minicpm-challenge)
#5499
opened Jul 28, 2026 by
natureofnature
Contributor
Loading…
[Bugfix] Default missing legacy stage input sources
#5498
opened Jul 28, 2026 by
wuli666
Contributor
Loading…
[XPU][Feat] enable sleep mode support on intel GPU
#5485
opened Jul 28, 2026 by
yma11
Contributor
Loading…
[skip ci][Misc] remove stray md introduced in #4652
#5473
opened Jul 28, 2026 by
fhfuih
Contributor
Loading…
[Feature][Qwen3-TTS] Add resumable WebSocket speech input
#5470
opened Jul 28, 2026 by
iancarrasco-b10
Contributor
•
Draft
4 of 6 tasks
[Perf] MiniCPM-o 4.5 thinker cuda graph
Kernel optimization
Codes related to optimize kernel execution to improve hardware utilization
omni
code related to omni models
#5466
opened Jul 27, 2026 by
nagisa-kunhah
Contributor
•
Draft
[bugfix][MiniCPM-o] Fix offline_inference/test_minicpmo_4_5.py and online_serving/ one
bug
Something isn't working
merge-test
label to trigger buildkite merge test CI
omni
code related to omni models
ready
label to trigger buildkite CI
[Refactor] Migrate Lance to standard task examples + model_extras
refactor
refactoring for better code scalability and quality
#5462
opened Jul 27, 2026 by
lulugoodcoder
Contributor
Loading…
[Refactor][1/N Scheduler]Remove duplicated AR/generation scheduler plumbing and establish explicit shared lifecycle contracts.
core
related to core module: cache, scheduler, engine, worker, modelrunner
refactor
refactoring for better code scalability and quality
#5461
opened Jul 27, 2026 by
R2-Y
Contributor
Loading…
Previous Next
ProTip!
Exclude everything labeled
bug with -label:bug.