MrDongslsandMr.Dong 825ab20b07 [Model][PersonaPlex] add per-row RingKV offsets and active rows (#7670) ...

Signed-off-by: Mr.Dong <1042542469@qq.com>
Co-authored-by: Mr.Dong <1042542469@qq.com>

2026-09-17 01:50:40 -07:00

..

assets

[Feat] Add support and testcase for HunyuanImage-3.0-Instruct-Distil (#4048)

2026-09-03 02:43:13 +00:00

attention

[BugFix][NPU] Fix Fish Speech S2 Pro NPU support (#7546)

2026-09-16 11:38:06 -07:00

benchmarks

[Bugfix] Reject failed diffusion benchmark warmups (#7092)

2026-09-16 17:09:23 +00:00

buildkite

[CI][ROCm] Add non-blocking engine and model executor GPU coverage (#7397)

2026-09-15 13:24:34 +08:00

clients

[Bugfix] Fail a duplex session that outgrows max_model_len instead of killing the EngineCore (#7277)

2026-09-16 20:08:25 +08:00

config

[Core] Retain structured configs through runtime startup (#6849)

2026-09-16 20:47:38 -07:00

core

[Bugfix] Fail a duplex session that outgrows max_model_len instead of killing the EngineCore (#7277)

2026-09-16 20:08:25 +08:00

dfx

[Bugfix] Preserve benchmark metric sample counts in results (#7624)

2026-09-16 08:39:01 -07:00

diffusion

[Diffusion][Model] Add direct FastH3 8-Step V2 checkpoint loading (#7610)

2026-09-17 08:41:52 +00:00

distributed

[Performance] Optimize MammothModa2 AR → DiT hidden-state transfer (#7102)

2026-09-14 15:25:08 -07:00

docs

[Core][Diffusion] Add a typed pre-D2H video media contract (#6615)

2026-09-10 09:50:54 +00:00

e2e

[CI] Fix Structured Structured Diffusion Config Wan Test (#7707)

2026-09-17 00:01:01 -07:00

engine

[Frontend] Scale Omni serving across API processes (#6923)

2026-09-16 22:29:31 -07:00

entrypoints

[Frontend] Scale Omni serving across API processes (#6923)

2026-09-16 22:29:31 -07:00

examples

[Hardware][Ascend] Add Wan2.2 MXFP4 UOS, Smooth and W4A8 fallback (#7210)

2026-09-17 03:11:40 +00:00

helpers

[Bugfix] Fix Qwen3-TTS word timestamps with async chunking (#7544)

2026-09-16 15:07:52 -07:00

host_weight_runtime

[Bugfix][Core] Clean up failed HWR atomic metadata writes (#6956)

2026-09-11 09:03:26 +08:00

inputs

[Rebase] Rebase to vLLM 0.29.0 (#7230)

2026-09-10 12:08:28 +08:00

metrics

[Feature][TTS] Add Speech API streaming metrics (#6853)

2026-09-11 21:22:15 +08:00

model_executor

[Model][PersonaPlex] add per-row RingKV offsets and active rows (#7670)

2026-09-17 01:50:40 -07:00

model_extras

[Model][MiniMax-H3] Multi-GPU serving fixes and layer-wise offload component selection (#7047)

2026-09-14 10:02:30 -07:00

model_tests

[Tests] Test image edit input limits in tiny model framework (#7434)

2026-09-15 12:36:34 -04:00

platforms

[Hardware][Ascend] Add Wan2.2 MXFP4 UOS, Smooth and W4A8 fallback (#7210)

2026-09-17 03:11:40 +00:00

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

rl_rollout

[P0][RFC #3747] RL rollout serving: session management + world_model_env (#4770)

2026-09-14 09:26:44 +08:00

tools

[Refactor] Declare model-local KV held outside the paged manager (#6171)

2026-09-11 08:44:32 +08:00

utils

[Bugfix] Build the forced-aligner prompt without a chat template (word timestamps one bin late) (#7240)

2026-09-08 19:27:38 +00:00

worker

[Core][Frontend] Unified Full-duplex Framework (#7413)

2026-09-16 15:35:36 +08:00

__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