hsliu_ustc and Claude Opus 4.7
15e5a708cc
[Docs] Update README supported models section with TTS and Diffusion categories
...
Expand the supported models overview to reflect the three model categories
currently supported: omni-modality, TTS, and diffusion.
Signed-off-by: hsliu_ustc <hsliu_ustc@noreply.gitcode.com >
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-06-10 10:26:18 +08:00
wuhang
0d9d57acd9
[Entrypoint][Refactor] Make field type hint more concrete ( #3139 )
...
Signed-off-by: wuhang <wuhang6@huawei.com >
2026-05-14 11:25:55 +08:00
Y. Fisher
51b4b1131e
[Bugfix]: Fix online serving failure when using deploy config ( #3537 )
...
Signed-off-by: KexiongYu <yukexiong1@huawei.com >
Signed-off-by: Y. Fisher <yukexiong1@huawei.com >
2026-05-14 11:17:15 +08:00
zhumingjue138
e818dba016
[Test] Add stability tests for HunyuanImage-3-Instruct ( #3504 )
...
Signed-off-by: zhumingjue <zhumingjue@huawei.com >
2026-05-14 10:47:14 +08:00
Alex Brooks
754d2e52fc
[BugFix] Refresh TeaCache when num_inference_steps=None ( #2240 )
...
Signed-off-by: Alex Brooks <albrooks@redhat.com >
2026-05-13 20:20:18 +00:00
vraiti and Claude Opus 4.6
9de9d1f7b5
[Model] Add TP-aware MistralEncoder for FLUX.2-dev TP ( #2465 )
...
Signed-off-by: vraiti <vraiti@redhat.com >
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com >
2026-05-13 12:33:55 -07:00
dengyunyang
efd955674b
[Bugfix][HunyuanImage3.0] Fix KV reuse compatibility in SP scenarios ( #3546 )
...
Signed-off-by: dengyunyang <584797741@qq.com >
2026-05-13 22:40:18 +08:00
Y. Fisher
4d3eed152a
[Feat][Config] Support additional_config for diffusion worker ( #3020 )
...
Signed-off-by: KexiongYu <yukexiong1@huawei.com >
Signed-off-by: Y. Fisher <yukexiong1@huawei.com >
2026-05-13 14:22:43 +00:00
Zeng Chuang
16a84b29d5
[Bugfix] Add bot_task option of think_recaption for hunyuanimage3 it2i ( #3551 )
...
Signed-off-by: zengchuang <zengchuang3@huawei.com >
2026-05-13 22:10:35 +08:00
TJian
b9cb57b631
[ROCm] Bugfix wan22 ( #3463 )
...
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com >
2026-05-13 20:50:57 +08:00
amy-why-3459
2e8e3057bc
[skip ci][Tests] Splitting Qwen3-omni's performance test cases ( #3501 )
...
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com >
2026-05-13 17:54:21 +08:00
hxhhhlalala and hyh_hh
a715abd447
[NPU][Quant] Add W8A8 MXFP8 online/offline quantization support for Wan2.2 T2V / I2V / TI2V inference on Ascend NPU ( #3140 )
...
Signed-off-by: hyh_hh <huyinghong1@huawei.com >
Co-authored-by: hyh_hh <huyinghong1@huawei.com >
2026-05-13 17:14:42 +08:00
weizhoublue and weizhoublue
b6bdc5997f
Fix: NPU AR model runner prefix cache key flattening ( #3568 )
...
Signed-off-by: weizhoublue <weizhoublue@github.com >
Signed-off-by: weizhou.lan@daocloud.io <weizhou.lan@daocloud.io >
Co-authored-by: weizhoublue <weizhoublue@github.com >
2026-05-13 08:22:48 +00:00
knlnguyen1802 and Samit
631251a1f8
[Bugfix, rl] Diffusion worker SIGKILL under Ray actor (exitcode -9) ( #3533 )
...
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com >
Co-authored-by: Samit <285365963@qq.com >
2026-05-13 15:31:48 +08:00
wangyu
b6f29ee614
[CI][Bugfix] skip fp8 Z-Image quality gate ( #3531 ) and add torchdiffeq dev extra ( #3563 )
...
Signed-off-by: wangyu <410167048@qq.com >
2026-05-13 14:25:56 +08:00
Canlin Guo
0ab1d30056
[CI][Test] Add NPU nightly tests ( #3480 )
...
Signed-off-by: gcanlin <canlinguosdu@gmail.com >
2026-05-13 16:58:17 +12:00
56ca7dd612
support online FP8 quantization for FA on NPU #2236 ( #2640 )
...
Signed-off-by: lyj-jjj <liuyingjun5@huawei.com >
Signed-off-by: gcanlin <canlinguosdu@gmail.com >
Co-authored-by: Cursor <cursoragent@cursor.com >
Co-authored-by: gcanlin <canlinguosdu@gmail.com >
2026-05-13 11:46:00 +08:00
Ricardo Noriega
83bbe39d39
Bump diffusers minimum version to >=0.38.0 ( #3349 )
...
Signed-off-by: Ricardo Noriega De Soto <rnoriega@redhat.com >
2026-05-13 10:25:02 +08:00
Nick Cao and Claude Opus 4.6
5313cf6d48
[Bugfix] Fix omni processing test for non-multimodal talker stage ( #3559 )
...
Signed-off-by: Nick Cao <ncao@redhat.com >
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-05-13 10:08:23 +08:00
zhumingjue138
c167b9d691
[Bugfix] Fix the issue where the qwen3-omni model long-term stability test sometimes gets stuck without sending requests. ( #3468 )
...
Signed-off-by: zhumingjue <zhumingjue@huawei.com >
2026-05-13 09:15:20 +08:00
Nick Cao and Claude
dca369d448
[Perf] Remove dead audio_tower and visual from Qwen2.5-Omni talker stage ( #3425 )
...
Signed-off-by: Nick Cao <ncao@redhat.com >
Co-authored-by: Claude <noreply@anthropic.com >
2026-05-12 23:24:13 +08:00
rein yang
f4b28f2398
[CI] update daily omni min accuracy ( #3536 )
...
Signed-off-by: rein yang <ruiruyang2@gmail.com >
2026-05-12 22:10:10 +08:00
knlnguyen1802 and Samit
aa1184d737
[bugfix, rl] Fix race condition bug on async running for diffusion model ( #3379 )
...
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com >
Co-authored-by: Samit <285365963@qq.com >
2026-05-12 14:55:30 +08:00
d7ea5d5979
[New Model] Add support for tencent/Covo-Audio-Chat ( #2293 )
...
Signed-off-by: Dnoob <dxpouo@gmail.com >
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com >
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-05-12 14:39:58 +08:00
dsinghvi
e40076e872
[Refactor] msgspec standardisation for data entry key names and improved type checks ( #3149 )
...
Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com >
Signed-off-by: dsinghvi <divyanshsinghvi@gmail.com >
2026-05-12 14:30:13 +08:00
NumberWan
9a60e11e3d
[Nightly CI] Remove TP case ( #3534 )
...
Signed-off-by: NumberWan <wantszkin2003@gmail.com >
2026-05-12 05:59:04 +00:00
Saad Al-Tohamy and Gao Han
fe72d078ca
[FIX] Ensure extra_params are correctly merged into sampling params in _create_diffusion_speech() ( #3320 )
...
Signed-off-by: saadaltohamy <saad_altohamy@yahoo.com >
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk >
2026-05-12 01:10:04 -04:00
dengyunyang and Hongsheng Liu
0d91fbbbb7
[Bugfix] Align the AR and DiT prompt formatting across both online and offline modes. ( #3516 )
...
Signed-off-by: dengyunyang <584797741@qq.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-05-12 12:13:30 +08:00
amy-why-3459
ce621be29b
[BugFix] Modify the splicing method of streaming audio output. ( #3438 )
...
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com >
2026-05-12 11:56:10 +08:00
bjf-frz
dd5626e607
[Recipes]update Wan2.2-I2V gpu part ( #3271 )
...
Signed-off-by: bjf-frz <frz123db@gmail.com >
2026-05-12 10:44:20 +08:00
wangyu
ac5fbed6c0
[CI][Bugfix] Improve e2e latency logging, update response classes to include detailed latency documentation and add startup time logging ( #3246 )
...
Signed-off-by: wangyu <410167048@qq.com >
Signed-off-by: [Your Name] <your.email@example.com >
2026-05-12 10:23:56 +08:00
Lancer
955fcff828
[Chore] explicit .float() conversion in Helios's optimized_scale function ( #3529 )
...
Signed-off-by: Lancer <maruixiang6688@gmail.com >
2026-05-12 02:08:28 +00:00
ChenWenjing
4bca522f01
[bugfix][ci] avoid Whisper transcript deduplication in realtime audio test ( #3417 )
...
Signed-off-by: CHEN <116010019@link.cuhk.edu.cn >
2026-05-11 17:09:10 +00:00
Nick Cao and Claude
bd4ede391b
[Perf] Remove dead audio_tower and visual from Qwen3-Omni talker stage ( #3296 )
...
Signed-off-by: Nick Cao <ncao@redhat.com >
Co-authored-by: Claude <noreply@anthropic.com >
2026-05-11 16:04:56 +00:00
Junhong Liu
6be59f7d19
[Fix] Fix RMSNorm inductor KeyError under HSDP + torch.compile ( #3460 )
...
Signed-off-by: Junhong Liu <98734602+LJH-LBJ@users.noreply.github.com >
2026-05-11 22:56:54 +08:00
Y. Fisher
a33e2eb588
[Config] Add HunyuanImage3 deploy configs ( #3172 )
...
Signed-off-by: KexiongYu <yukexiong1@huawei.com >
Signed-off-by: Y. Fisher <yukexiong1@huawei.com >
2026-05-11 22:49:19 +08:00
汪志鹏
c9a8556c24
[New Model]: Add sensenova u1 support ( #3319 )
...
Signed-off-by: princepride <wangzhipeng628@gmail.com >
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com >
2026-05-11 22:19:00 +08:00
wangyu
2cdffcea6b
[CI] skip failing diffusion and accuracy cases ( #3432 , #3256 , #3257 , #3488 ) ( #3507 )
...
Signed-off-by: wangyu <410167048@qq.com >
2026-05-11 21:56:08 +08:00
wuhang
3f27ffbd4d
[Misc] Clean logs for image gen task ( #3414 )
...
Signed-off-by: wuhang <wuhang6@huawei.com >
2026-05-11 12:16:05 +00:00
dengyunyang
3bf4f2850c
[Bug][Hunyuanimage 3.0] fix different AR encode behavior between online and offline ( #3500 )
...
Signed-off-by: dengyunyang <584797741@qq.com >
2026-05-11 11:34:58 +00:00
Canlin Guo
5e263b6929
[BugFix] Rename attention_config to diffusion_attention_config ( #3489 )
...
Signed-off-by: gcanlin <canlinguosdu@gmail.com >
2026-05-11 11:27:35 +08:00
e1088026fa
[Performance] Improve MiMo-Audio tokenizer decoding performance ( #2183 )
...
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com >
Co-authored-by: Jialong Liu <88185941+Galleons2029@users.noreply.github.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-05-11 10:05:46 +08:00
Canlin Guo and Hongsheng Liu
ef7f2f1cd2
[Docs] Refactor the attention backend docs/skill ( #3475 )
...
Signed-off-by: gcanlin <canlinguosdu@gmail.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-05-11 09:13:07 +08:00
TJian
67e0e10c85
[ROCm] [CI] Add the same skip ci logic as CUDA CI ( #3482 )
...
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com >
2026-05-11 07:53:27 +08:00
Sy03
2c73cf3522
[Perf] Fix Qwen3-TTS latency regression ( #3485 )
...
Signed-off-by: Sy03 <1370724210@qq.com >
2026-05-10 23:07:38 +00:00
dengyunyang
857356d5b7
[Feature] hunyuanimage support flash attn ( #2981 )
...
Signed-off-by: dengyunyang <584797741@qq.com >
2026-05-10 22:08:24 +08:00
Canlin Guo and Hongsheng Liu
11c4c7f0ff
[Diffusion][Attention] Support per-role attention backend via CLI ( #2681 )
...
Signed-off-by: gcanlin <canlinguosdu@gmail.com >
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-05-10 11:59:05 +08:00
wangyu and Hongsheng Liu
26d481fc84
[CI] Remove VLLM_TEST_CLEAN_GPU_MEMORY to avoid environment variable pollution that causes unnecessary GPU detection, thereby slowing down test case execution. ( #3446 )
...
Signed-off-by: wangyu <410167048@qq.com >
Signed-off-by: [Your Name] <your.email@example.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-05-10 07:00:29 +08:00
wuhang
77480215f5
[CI][Nightly] Shard nightly Diffusion X2I H100 lanes and centralize shard definitions ( #3455 )
...
Signed-off-by: wuhang <wuhang6@huawei.com >
2026-05-09 21:13:18 +08:00
baonudesifeizhai and roG0d
c4a0990044
(Phase 1)Add ModelOpt FP8 auto-detect support for diffusion checkpoints #2709 ( #2913 )
...
Signed-off-by: roG0d <rodgarcas98@gmail.com >
Signed-off-by: roG0d <baonudesifeizhai@gmail.com >
Signed-off-by: baonudesifeizhai <85092850+baonudesifeizhai@users.noreply.github.com >
Co-authored-by: roG0d <rodgarcas98@gmail.com >
2026-05-09 16:55:05 +08:00