3 people 21dd4b33ac [Bugfix][MiniCPM-o] Stabilize native duplex streaming and Stage-1 handoffs (#6529) ...

Signed-off-by: Sy03 <1370724210@qq.com>
Co-authored-by: Nathan Price <nathan@abridge.com>
Co-authored-by: Eric(Qun) <186020953+0xtoward@users.noreply.github.com>

2026-08-29 13:05:24 -07:00

..

assets

[CI]Remove SoulX-Singer support (#6362)

2026-08-23 07:16:32 +08:00

attention

[Rebase] Rebase to vllm 0.26.0 (#5443)

2026-07-27 23:35:49 +08:00

benchmarks

[Bugfix] Avoid invalid TPOT metrics (#6696)

2026-08-29 11:56:37 +00:00

buildkite

[CI/Build] Move L1/E2E coverage to weekly and split scheduled L4/L5 pipelines (#6311)

2026-08-23 11:49:37 +08:00

config

Fix MiniCPM-o concurrent audio first-packet latency (#6767)

2026-08-29 23:27:47 +08:00

core

[Bugfix][MiniCPM-o] Stabilize native duplex streaming and Stage-1 handoffs (#6529)

2026-08-29 13:05:24 -07:00

dfx

[Bugfix] Avoid invalid TPOT metrics (#6696)

2026-08-29 11:56:37 +00:00

diffusion

[diffusion][bugfix] Separate Diffusers hooks from model metadata (#6749)

2026-08-29 17:37:14 +00:00

distributed

[Bugfix][MiniCPM-o] Stabilize native duplex streaming and Stage-1 handoffs (#6529)

2026-08-29 13:05:24 -07:00

docs

[Bugfix] Stop reading the removed OmniRequestOutput.request_output accessor (#6172)

2026-08-15 07:07:28 +08:00

e2e

[CI]Split GPU jobs by cards_* and reject hand-written SKU marks (#6650)

2026-08-29 18:42:33 +08:00

engine

[Bugfix][MiniCPM-o] Stabilize native duplex streaming and Stage-1 handoffs (#6529)

2026-08-29 13:05:24 -07:00

entrypoints

[Bugfix][MiniCPM-o] Stabilize native duplex streaming and Stage-1 handoffs (#6529)

2026-08-29 13:05:24 -07:00

examples

[video][bugfix] Accept semantic video output in offline examples (#6747)

2026-08-29 06:26:28 +00:00

helpers

[CI]Split GPU jobs by cards_* and reject hand-written SKU marks (#6650)

2026-08-29 18:42:33 +08:00

host_weight_runtime

[Bugfix] Make HWR filesystem lifecycle transitions fail-closed (#6692)

2026-08-28 09:30:17 +08:00

inputs

[Model][Feat] Support Minimax-H3 quality grading requests through dynamic loading/unloading with Cache-DiT (#5853)

2026-08-07 09:07:23 +00:00

metrics

[Bugfix] Report engine-queued requests as waiting in vllm_omni:num_requests gauges (#6549)

2026-08-29 03:58:26 +00:00

model_executor

[Bugfix][MiniCPM-o] Bound full-duplex Talker context with sliding recompute (#6626)

2026-08-30 00:49:42 +08:00

model_extras

[Fix] Restore MammothModa2 support (#6694)

2026-08-28 08:32:32 +08:00

model_tests

[Diffusion] Make Flux2Pipeline text_encoder_out_layers configurable (#6390)

2026-08-28 09:05:41 -06:00

platforms

[Bugfix][NPU] Eager-import mindiesd for every diffusion attention backend (#6054)

2026-08-27 14:41:36 +08:00

profile

[Refactor][CI] Reorganize test tree, and move slow e2e to weekly (#4951)

2026-07-29 23:53:03 +08:00

quantization

[Refactor][CI] Reorganize test tree, and move slow e2e to weekly (#4951)

2026-07-29 23:53:03 +08:00

reasoning

[Refactor][CI] Reorganize test tree, and move slow e2e to weekly (#4951)

2026-07-29 23:53:03 +08:00

tools

[Migrate] Move sampling parameter overrides from legacy dispatches to TTS adapters (#5272)

2026-08-16 21:14:26 -07:00

utils

[Test] Cleanup for helpers (#6523)

2026-08-25 09:10:17 +08:00

worker

[Bugfix] Fix colocate-async sleep admission race and deliver AR abort tokens (#6367)

2026-08-29 09:11:39 +00:00

__init__.py

[Fix] Resolve comments & update vLLM-Omni name usages. (#122)

2025-12-01 08:05:24 +08:00

conftest.py

[CI]Split GPU jobs by cards_* and reject hand-written SKU marks (#6650)

2026-08-29 18:42:33 +08:00