 Taichang Zhou
|
b1073a6e7f
|
Merge branch 'dev/rebase-v0170' of https://github.com/vllm-project/vllm-omni into dev/rebase-v0170
|
2026-03-09 23:40:54 +08:00 |
|
|
Taichang Zhou
|
0940c5a05e
|
Merge remote-tracking branch 'remotes/origin/main' into dev/rebase-v0170
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
|
2026-03-09 23:40:32 +08:00 |
|
|
Didan Deng
|
e79ad8d59a
|
[Doc] CLI Args Naming Style Correction (#1750)
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
|
2026-03-09 23:35:45 +08:00 |
|
|
Yuanheng Zhao
|
82f63a4403
|
[BugFix] Enable CPU offloading and Cache-DiT together on Diffusion Model (#1723)
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
|
2026-03-09 22:25:41 +08:00 |
|
|
汪志鹏
|
7271116973
|
[Bagel]: Support multistage img2img (#1669)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
|
2026-03-09 22:23:50 +08:00 |
|
|
wangyu
|
5628d41242
|
[Test] Solving the Issue of Whisper Model's GPU Memory Not Being Successfully Cleared and the Occasional Accuracy Problem of the Qwen3-omni Model Test (#1744)
Signed-off-by: yenuo26 <410167048@qq.com>
|
2026-03-09 21:52:56 +08:00 |
|
|
Samit
|
155856ff30
|
[Perf] Reduce IPC overhead for single-stage diffusion serving for Wan2.2 (#1715)
Signed-off-by: samithuang <285365963@qq.com>
Signed-off-by: Samit <285365963@qq.com>
v0.17.0rc1
|
2026-03-10 00:03:51 +13:00 |
|
|
|
89b527e533
|
Dev/rebase v0170 (#1639)
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
|
2026-03-09 17:29:38 +08:00 |
|
|
tzhouam
|
a9b4367808
|
Update GPU memory utilization and max number of batched tokens in qwen3_omni.yaml to optimize resource allocation during model execution.
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2026-03-09 08:22:26 +00:00 |
|
|
tzhouam
|
79626586e1
|
Update GPU memory utilization in qwen3_omni.yaml from 0.6 to 0.45 to prevent out-of-memory errors during model execution.
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2026-03-09 08:02:25 +00:00 |
|
|
Yueqian Lin
|
4db10d6dec
|
Disable mm processor cache in CI stage configs (#1739)
Signed-off-by: linyueqian <linyueqian@outlook.com>
|
2026-03-09 15:42:15 +08:00 |
|
|
Canlin Guo
|
29357027b0
|
[Bugfix] Allow to enable HSDP alone (#1567)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
|
2026-03-09 06:36:13 +00:00 |
|
|
tzhouam
|
e6d4cdd71a
|
Refactor model mode initialization and enhance error handling in AsyncOmni. Update worker type retrieval in omni_stage and add audio token handling in Qwen3OmniMoe classes for improved robustness.
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2026-03-09 06:17:08 +00:00 |
|
|
|
d6871db6a3
|
[Feat]: Offline inference supports async_chunk (#1415)
Signed-off-by: Sy03 <1370724210@qq.com>
Signed-off-by: linyueqian <linyueqian@outlook.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: linyueqian <linyueqian@outlook.com>
|
2026-03-09 11:33:38 +08:00 |
|
|
Ding Zuhaoandprincepride
|
fb717a4071
|
[Bagel] Eliminate broadcast in CFG parallel denoising loop (#1695)
Signed-off-by: Ding Zuhao <e1583181@u.nus.edu>
Co-authored-by: princepride <wangzhipeng628@gmail.com>
|
2026-03-09 03:26:21 +00:00 |
|
|
|
41964cb90a
|
feat(tts): add voice upload API for Qwen3-TTS (#1201)
Signed-off-by: linyueqian <linyueqian@outlook.com>
Co-authored-by: linyueqian <linyueqian@outlook.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
|
2026-03-09 11:02:11 +08:00 |
|
|
Shenghai Yuanandgcanlin
|
382bbd0a1f
|
[1/N] fix CP for Helios (#1729)
Signed-off-by: Shenghai Yuan <140951558+SHYuanBest@users.noreply.github.com>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: gcanlin <canlinguosdu@gmail.com>
|
2026-03-09 02:52:01 +00:00 |
|
|
Yueqian LinandHongsheng Liu
|
16248e97ef
|
Pre-download Qwen3-TTS model in CI to avoid intermittent download timeouts (#1727)
Signed-off-by: linyueqian <linyueqian@outlook.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
|
2026-03-09 15:12:45 +13:00 |
|
|
knlnguyen1802andSamit
|
92e1a54419
|
[RL] Support collective rpc api to entrypoint && Support custom input output (#1646)
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Signed-off-by: Samit <285365963@qq.com>
Co-authored-by: Samit <285365963@qq.com>
|
2026-03-09 10:12:43 +08:00 |
|
|
Yueqian Lin
|
a9f694b08a
|
[Bugfix] Use upstream MediaConnector for ref_audio resolution (#1661)
Signed-off-by: linyueqian <linyueqian@outlook.com>
|
2026-03-09 01:38:26 +00:00 |
|
|
Roman Koshkin
|
0e432e524c
|
[Bugfix] (qwen3_tts): enable batched offline inference by fixing tens… (#1417)
Signed-off-by: Roman Koshkin <roman.koshkin@sbintuitions.co.jp>
|
2026-03-09 09:17:10 +08:00 |
|
|
|
bb051ab1df
|
[skip ci] Update slides link (#1730)
Signed-off-by: hsliu <liuhongsheng4@huawei.com>
Signed-off-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: hsliu_ustc <hsliu_ustc@noreply.gitcode.com>
|
2026-03-08 20:45:54 +08:00 |
|
|
Canlin Guo
|
c3a59f10f3
|
[NPU] Support Helios-Mid / Distilled (#1648)
|
2026-03-08 17:24:25 +08:00 |
|
|
Hongsheng Liu
|
9cdbcec44b
|
Merge branch 'main' into dev/rebase-v0170
|
2026-03-08 09:18:57 +08:00 |
|
|
Alicia
|
b255654a76
|
[CI] Add release-pipeline.yaml. (#1726)
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
|
2026-03-08 12:26:04 +13:00 |
|
|
Taichang Zhou
|
c8b695f181
|
smaller talker gpu util to avoid oom
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
|
2026-03-08 01:48:42 +08:00 |
|
|
Canlin Guo
|
074af30a9b
|
Revert "[Profile] Adding metrics for Diffusion/DiT Single diffusion Pipeline (#668)" (#1724)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
|
2026-03-08 00:11:47 +13:00 |
|
|
Taichang Zhou
|
f405240513
|
Change pytest fixture scope from "module" to "class" for omni_server and omni_server_no_async_chunk in test_qwen3_tts.py to improve test isolation and resource management.
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
|
2026-03-07 14:50:59 +08:00 |
|
|
Taichang Zhou
|
c630cf39c1
|
Enhance Dockerfile.ci by adding system dependencies installation and copying project files into the container. This improves the build process for the CI environment.
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
|
2026-03-07 14:02:48 +08:00 |
|
|
Taichang Zhou
|
3facc89dd1
|
Update base image in Dockerfile.rocm to v0.17.0 for improved compatibility and features.
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
|
2026-03-07 13:59:23 +08:00 |
|
|
Taichang Zhou
|
68bad871bc
|
Fix model detection logic in is_diffusion_model function to ensure config_dict is checked for None before accessing its fields. This improves robustness against missing model_index.json files.
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
|
2026-03-07 13:57:44 +08:00 |
|
|
Taichang Zhou
|
f945d2a30d
|
Refactor Dockerfile.ci to streamline installation process and update vllm-omni installation method. Removed commented-out installation commands and ensured Python symlink is created.
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
|
2026-03-07 13:57:23 +08:00 |
|
|
Taichang Zhou
|
315f9401db
|
Refactor imports in metrics.py and patch.py to use TokenizerLike from vllm.tokenizers instead of PreTrainedTokenizerBase from transformers.
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
|
2026-03-07 13:33:10 +08:00 |
|
|
Taichang Zhou
|
fd4607f215
|
rebase 2026/03/07
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
|
2026-03-07 13:30:58 +08:00 |
|
|
Taichang Zhou
|
0ecfff0694
|
comment out extra installation
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
|
2026-03-07 13:29:12 +08:00 |
|
|
Taichang Zhou
|
4a43c6b017
|
Merge branch 'dev/rebase-v0170' of https://github.com/vllm-project/vllm-omni into dev/rebase-v0170
|
2026-03-07 13:26:46 +08:00 |
|
|
Taichang Zhou
|
0c2464db20
|
revert unnecessary changes
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
|
2026-03-07 13:26:32 +08:00 |
|
|
Zhou TaichangandCyrus Leung
|
5f1e41970c
|
Update vllm_omni/benchmarks/patch/patch.py
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
|
2026-03-07 13:23:47 +08:00 |
|
|
Zhou TaichangandCyrus Leung
|
4ead1c8913
|
Update vllm_omni/benchmarks/metrics/metrics.py
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
|
2026-03-07 13:23:38 +08:00 |
|
|
Taichang Zhou
|
2187db0e36
|
Remove obsolete RFC documents for automated rebase agent, output processor refactor, model runner clearance, long function decomposition, and model runner V2 integration. These files are no longer relevant to the current project direction.
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
|
2026-03-07 13:22:39 +08:00 |
|
|
Taichang Zhou
|
5511bc14c7
|
Merge origin/main into dev/rebase-v0170
- Resolved conflict in vllm_omni/engine/output_processor.py: use tracing_enabled for vLLM v0.17.0 API
- Resolved conflict in vllm_omni/model_executor/models/qwen3_tts/qwen3_tts_code_predictor_vllm.py: keep correct _CodePredictorDecoderLayer.forward()
- Update Dockerfile.ci vLLM wheel commit to b31e9326a (releases/v0.17.0)
Made-with: Cursor
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
|
2026-03-07 13:18:33 +08:00 |
|
|
Taichang Zhou
|
3a6b2e27be
|
[Update] Bump VLLM base tag to v0.17.0 in CI Dockerfile
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
|
2026-03-07 13:14:10 +08:00 |
|
|
Didan Deng
|
30191ed112
|
[Feature]: Add vae-patch-parallel CLI argument in online serving (#1716)
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
|
2026-03-07 01:45:02 +08:00 |
|
|
erfgss
|
b7fcc9d07e
|
[Profile] Adding metrics for Diffusion/DiT Single diffusion Pipeline (#668)
Signed-off-by: Chen Yang <2082464740@qq.com>
Signed-off-by: erfgss <97771661+erfgss@users.noreply.github.com>
|
2026-03-06 15:39:19 +08:00 |
|
|
Yueqian Lin
|
411fe05bd4
|
[skip CI][Docs] Add TTS model developer guide (#1693)
Signed-off-by: linyueqian <linyueqian@outlook.com>
|
2026-03-06 14:49:19 +08:00 |
|
|
JohnJanandHongsheng Liu
|
92adcdeab4
|
[feature]: support flux2.klein cache_dit (#1209)
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
|
2026-03-06 14:46:57 +08:00 |
|
|
Canlin Guo
|
846167b237
|
[1/N][Refactor] Clean up dead code in output processor (#1579)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
|
2026-03-06 14:45:53 +08:00 |
|
|
Yueqian Lin
|
3bc89de0c0
|
Add non-async chunk support for Qwen3-TTS (#1678)
Signed-off-by: linyueqian <linyueqian@outlook.com>
|
2026-03-06 14:45:32 +08:00 |
|
|
Baoyuan Qi
|
32fd084ae2
|
[MiMo-Audio] Bugfix tp lg than 1 (#1688)
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2026-03-06 14:45:08 +08:00 |
|
|
Sy03
|
90ec499bd5
|
[Refactor][Perf] Qwen3-TTS: re-prefill Code Predictor with torch.compile + enable Code2Wav decoder CUDA Graph (#1617)
Signed-off-by: Sy03 <1370724210@qq.com>
|
2026-03-06 18:21:55 +13:00 |
|