 Mick
|
f7fc2c8592
|
[diffusion] fix: fix accuracy for some image models (#20679)
|
2026-03-22 15:11:57 +08:00 |
|
|
Mick
|
6dfa8a40bc
|
[diffusion] CI: make auxiliary coverage explicit and simplify testcases (#20983)
|
2026-03-21 20:18:23 +08:00 |
|
|
Mick
|
f15b3338c9
|
Revert "[Bugfix] Fix GLM-4.6V vision regression in glm4v_moe and glm_ocr" (#20740)
|
2026-03-18 10:09:50 +08:00 |
|
|
Mickandgemini-code-assist[bot]
|
5717834f1f
|
[diffusion] refactor: cleanup parallel_state.py (#20760)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2026-03-17 21:21:42 +08:00 |
|
|
Mick
|
5ec49a5309
|
Revert "[diffusion] CI: use dedicated HF token for accessing restricted models" (#20737)
|
2026-03-16 20:22:20 -07:00 |
|
|
Mick
|
474a851ae3
|
[diffusion] fix: fix sampling params incorrectly override in cli (#20689)
|
2026-03-17 08:48:10 +08:00 |
|
|
Mick
|
1eea744855
|
[diffusion] CI: enable UT (#20690)
|
2026-03-17 07:44:04 +08:00 |
|
|
Mick
|
485597e651
|
[diffusion] fix: fix some sampling args passed via cli are omitted (#20630)
|
2026-03-16 16:55:30 +08:00 |
|
|
Mick
|
f07529b947
|
[diffusion] CI: use dedicated HF token for accessing restricted models (#20620)
|
2026-03-15 19:15:28 +08:00 |
|
|
Mick
|
b638b25b22
|
[diffusion] UX: suppress excessive logging from httpx and httpcore (#20452)
|
2026-03-13 14:43:09 +08:00 |
|
|
Mick
|
154af9e46c
|
update CI_PERMISSIONS.json (#20405)
|
2026-03-12 19:50:35 -07:00 |
|
|
Mick
|
8c8a487468
|
[diffusion] doc: add diffusion-optimal-perf (#20311)
|
2026-03-11 12:20:09 +08:00 |
|
|
Mick
|
e1f0b3181a
|
[diffusion] fix: adjust convert_hf_to_fp8 to be compatible with more dits (#20281)
|
2026-03-11 01:21:54 +08:00 |
|
|
Mick
|
2c183350be
|
[diffusion] fix: fix wrong dit config for qwen-image-edit-plus-2511 (#20123)
|
2026-03-08 20:08:36 +08:00 |
|
|
Mick
|
d605d811fb
|
update CODEOWNERS (#19969)
|
2026-03-05 10:19:05 -08:00 |
|
|
Mick
|
43a9249e7c
|
CI: update CI_PERMISSIONS.json (#19744)
|
2026-03-02 22:34:41 -08:00 |
|
|
Mick
|
2e15c015c0
|
[diffusion] feat: Add --model-id for config resolution; deprecate model_detectors (#19607)
|
2026-03-02 16:39:53 +08:00 |
|
|
Mick
|
a75840b373
|
[diffusion] CI: create and refactor UT (#19619)
|
2026-03-01 19:38:20 +08:00 |
|
|
Mick
|
d098c8dab0
|
[diffusion] add .claude and update contributing with attitude towards vibe-pr (#19511)
|
2026-03-01 14:41:55 +08:00 |
|
|
Mick
|
471acd98b9
|
[diffusion] logging: improve logging (#19312)
|
2026-02-25 23:00:35 +08:00 |
|
|
Mick
|
9840cd3f68
|
[diffusion] chore: enable sequence shard for wan by default (#19311)
|
2026-02-25 18:21:44 +08:00 |
|
|
Mick
|
aff2f130ec
|
[diffusion] CI: fix pr-test workflow file to include changes in jit kernels (#19285)
|
2026-02-25 14:08:55 +08:00 |
|
|
Mick
|
241ee90164
|
[diffusion] chore: tiny fix pyproject.toml (#19256)
|
2026-02-25 11:57:53 +08:00 |
|
|
Mick
|
0ede5c54a8
|
[diffusion] logging: improve request and component load logs (#19253)
|
2026-02-25 09:32:36 +08:00 |
|
|
Mickandzyzshishui
|
2e053d6eb6
|
[diffusion] quant: support quant for all dits (#19156)
Co-authored-by: zyzshishui <zyzshishui@gmail.com>
|
2026-02-24 14:20:54 +08:00 |
|
|
Mick
|
45095bac70
|
[diffusion] refactor: rename quantized model path server arg (#19142)
|
2026-02-22 23:18:35 +08:00 |
|
|
Mick
|
7d4860bc5e
|
[diffusion] CI: relax perf check threshold (#19154)
|
2026-02-22 20:02:12 +08:00 |
|
|
Mick
|
87823722b3
|
[diffusion] chore: minor cleanups (#19123)
|
2026-02-22 19:07:25 +08:00 |
|
|
Mick
|
6503f94211
|
[diffusion] feat: support passing component path via server args (#19108)
|
2026-02-21 21:22:47 +08:00 |
|
|
Mick
|
b89ca65789
|
[diffusion] refactor: reduce redundancy and improve stage api (#19060)
|
2026-02-21 16:35:47 +08:00 |
|
|
Mick
|
8d789b5c3d
|
[diffusion] feat: support nunchaku for Z-Image-Turbo and flux.1 (int4) (#18959)
|
2026-02-20 21:16:08 +08:00 |
|
|
Mick
|
38a69652e6
|
[diffusion] logging: log available mem when each stage starts in debug level (#18998)
|
2026-02-20 19:57:06 +08:00 |
|
|
Mick
|
3207427d6d
|
[diffusion] CI: enable warmup as default (#19010)
|
2026-02-19 23:27:23 +08:00 |
|
|
Mick
|
d73f06f091
|
[diffusion] chore: improve memory usage on consumer-level GPU (#18997)
|
2026-02-19 21:59:49 +08:00 |
|
|
Mick
|
420a611275
|
[diffusion] refactor: unify SamplingParams construction and improve DiffGenerator return types (#18928)
|
2026-02-18 14:56:58 +08:00 |
|
|
Mick
|
bfe34c90ff
|
Revert "[diffusion] operator: unify rotary embedding impl" (#18929)
|
2026-02-17 22:56:04 +08:00 |
|
|
Mick
|
de833f9e8e
|
Revert "[diffusion]: Improve layerwise offload buffer reuse and shared-storage handling" (#18866)
|
2026-02-16 18:00:58 +08:00 |
|
|
Mick
|
d0c94e136a
|
[diffusion] logging: improve peak vram logging (#18865)
|
2026-02-16 16:44:37 +08:00 |
|
|
Mick
|
0af9dcc407
|
[diffusion] refactor: refactor server_args adjust and validate logics (#18863)
|
2026-02-16 11:49:06 +08:00 |
|
|
Mick
|
78b4c9e248
|
[diffusion] fix: avoid saving output for warmup requests (#18867)
|
2026-02-16 11:48:28 +08:00 |
|
|
|
3feb48139e
|
[diffusion] quant: add support for svdquant and nunchaku (#18549)
Co-authored-by: AichenF <aichenf@nvidia.com>
Co-authored-by: jianyingzhu <53300651@qq.com>
|
2026-02-15 20:43:00 +08:00 |
|
|
Mick
|
37273408eb
|
[diffusion] chore: use batched P2P ops in VAE parallel decoding (#18728)
|
2026-02-13 22:11:20 +08:00 |
|
|
Mick
|
efdd676d56
|
[diffusion] refactor: merge redundant default_dtype and param_dtype parameters in FSDP loader (#18789)
|
2026-02-13 21:18:02 +08:00 |
|
|
Mick
|
efcdda0176
|
[diffusion] fix: fix fsdp (#18187)
|
2026-02-10 20:22:20 +08:00 |
|
|
Mick
|
4f7da5ad0f
|
[diffusion] chore: fix unclean shutdown and resource leaks (#18477)
|
2026-02-09 22:32:08 +08:00 |
|
|
Mick
|
6601bc24da
|
[diffusion] chore: revise process title (#18446)
|
2026-02-09 00:14:06 +08:00 |
|
|
Mick
|
a41aff1243
|
[diffusion] refactor: group component loaders under the component_loaders/ directory (#18438)
|
2026-02-08 23:02:27 +08:00 |
|
|
Mick
|
31d4cd2ffd
|
[diffusion] fix: respect dist_timeout option (#18386)
|
2026-02-07 20:56:04 +08:00 |
|
|
Mick
|
f218234e4f
|
[diffusion] chore: prohibit Chinese characters usage (#18249)
|
2026-02-05 09:22:26 +08:00 |
|
|
Mick
|
36a3e78af9
|
[diffusion] refactor: move model_stages into stages folder (#18248)
|
2026-02-05 00:23:31 +08:00 |
|
|
Mick
|
62004fd2be
|
[diffusion] UX: improve logging (#18122)
|
2026-02-03 10:35:05 +08:00 |
|
|
Mick
|
c84cd4b5ff
|
[diffusion] fix: fix missing component names for VAELoader (#18069)
|
2026-02-02 09:48:17 +08:00 |
|
|
Mick
|
977096ae03
|
[diffusion] cli: introduce generic attention backend configuration in ServerArgs (#18036)
|
2026-02-02 09:47:40 +08:00 |
|
|
Mick
|
1a006c2a0d
|
[diffusion] refactor: split component_loader into component-wise files (#17820)
|
2026-01-31 20:22:31 +08:00 |
|
|
Mick
|
2573a262af
|
[diffusion] doc: fix wrong docker run command (#17856)
|
2026-01-28 14:52:33 +08:00 |
|
|
Mick
|
88fcd8535f
|
[diffusion] feat: add an arg for controlling the number of prefetched layers in layerwise-offload (#17693)
|
2026-01-28 09:34:27 +08:00 |
|
|
Mick
|
1507dc6cdf
|
[diffusion] fix: fix suppressing error log on non-main ranks (#17712)
|
2026-01-28 09:29:19 +08:00 |
|
|
Mick
|
b105dad5da
|
[diffusion] refactor: remove useless lazy-import cache-dit codes (#17659)
|
2026-01-25 22:43:22 +08:00 |
|
|
MickandXiaoyu Zhang
|
51f147ada3
|
Update CODEOWNERS for multimodal_gen (#17308)
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
|
2026-01-19 08:39:20 +08:00 |
|
|
Mick
|
09491a9bcd
|
cli: support sglang version (#17250)
|
2026-01-18 13:20:24 +08:00 |
|
|
Mick
|
dc743fe4ba
|
[diffusion] chore: clean srt imports (#17252)
|
2026-01-17 15:47:49 +08:00 |
|
|
Mick
|
eb768189ee
|
[diffusion] doc: add instruction for adding performance baseline of new model (#17249)
|
2026-01-17 12:24:59 +08:00 |
|
|
Mick
|
16831ab6d7
|
[diffusion] fix: fix using upstream flash_attn on blackwell (#17111)
|
2026-01-15 22:30:48 +08:00 |
|
|
Mick
|
68e8d0f68d
|
[diffusion] CI: add testcase for cfg parallel (#17056)
|
2026-01-15 13:13:31 +08:00 |
|
|
Mick
|
a5348eac4c
|
[diffusion] chore: avoid raising error when output resolution is not optimal (#17030)
|
2026-01-14 11:36:27 +08:00 |
|
|
Mick
|
9524040220
|
[diffusion] chore: refactor warmup logic (#17027)
|
2026-01-14 11:35:06 +08:00 |
|
|
Mick
|
7a869045b6
|
[diffusion] chore: clean excessive document (#16986)
|
2026-01-13 21:33:50 +08:00 |
|
|
Mick
|
47d485f35f
|
[diffusion] fix: fix not respecting dit_layerwise_offload server arg (#16252)
|
2026-01-13 09:29:07 +08:00 |
|
|
Mick
|
2b42309955
|
[diffusion] UX: provide solutions for OOM (#16940)
|
2026-01-13 09:25:27 +08:00 |
|
|
Mick
|
badcd02896
|
[diffusion] chore: automatically enable dit_layerwise_offload for Wan (#16499)
|
2026-01-07 10:22:08 +08:00 |
|
|
Mick
|
ca922d4b05
|
[diffusion] feat: support warmup with resolutions (#16434)
|
2026-01-06 10:32:18 +08:00 |
|
|
Mick
|
9a8ba3c189
|
[diffusion] feat: support warmup with resolutions (#16330)
|
2026-01-05 10:16:26 +08:00 |
|
|
Mick
|
2c09de343e
|
[diffusion] improve: skip loading vision module for text encoders (#16304)
|
2026-01-03 19:30:45 +08:00 |
|
|
Mickandgemini-code-assist[bot]
|
38d48de93d
|
[diffusion] CI: simplify warmup (#16303)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2026-01-03 18:09:38 +08:00 |
|
|
Mickandgemini-code-assist[bot]
|
f26f6c2c99
|
[diffusion] fix: make lora compatible with layerwise-offload (#16298)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2026-01-02 22:33:26 +08:00 |
|
|
Mick
|
5062537b67
|
[diffusion] feat: support lightweight e2e warmup for benchmarking (#16213)
|
2026-01-02 20:10:27 +08:00 |
|
|
Mick
|
21de3e1406
|
[diffusion] webui: tiny fix loading output image (#16251)
|
2026-01-01 14:34:49 +08:00 |
|
|
Mickandgemini-code-assist[bot]
|
5bf0d862dd
|
[diffusion] CI: fix generate mode and add cli test (#16174)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2025-12-31 09:51:48 +08:00 |
|
|
Mick
|
3449806727
|
[diffusion] feat: generalize layer-wise-offload to all supported models (#16150)
|
2025-12-30 22:06:57 +08:00 |
|
|
Mick
|
1e45320198
|
[diffusion] improve: tiny improve layerwise offload manager by consolidating weights per layer (#16081)
|
2025-12-30 11:31:00 +08:00 |
|
|
Mick
|
26e17f9076
|
[diffusion] improve: tiny speedup qwen-image-edit-2511 by avoiding unnecessary calculation (#15896)
|
2025-12-30 10:10:32 +08:00 |
|
|
MickandXiaoyu Zhang
|
8e08207c18
|
[diffusion] fix: fix serving with dit-layerwise-offload enabled (#16066)
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
|
2025-12-30 00:21:42 +08:00 |
|
|
Mick
|
b5d9fc873b
|
[diffusion] chore: minor refactor by streamlining the VAE class hierarchy (#16069)
|
2025-12-29 23:37:59 +08:00 |
|
|
Mick
|
d7a3336ebe
|
[diffusion] fix: fix stages not logged when perf_dump_path is provided (#16016)
|
2025-12-28 23:17:43 +08:00 |
|
|
Mick
|
9f8e23071a
|
[diffusion] chore: fix default offload setting for image generation model (#15928)
|
2025-12-28 20:45:33 +08:00 |
|
|
Mick
|
3881bc8d0b
|
[diffusion] CI: relax threshold by supporting different profiles (#16002)
|
2025-12-28 20:05:07 +08:00 |
|
|
Mick
|
b4a00ed2d9
|
[diffusion] chore: clean ComposedPipelineBase (#15937)
|
2025-12-28 11:43:25 +08:00 |
|
|
Mick
|
39d56196a0
|
[diffusion] logging: log available gpu mem while loading and generating (#15936)
|
2025-12-28 00:34:58 +08:00 |
|
|
Mick
|
aa89c6a7e2
|
[diffusion] refactor: unify model loading and offloading behavior (#15923)
|
2025-12-27 16:18:24 +08:00 |
|
|
Mickandgemini-code-assist[bot]
|
b70914969b
|
[diffusion] CI: support returning request id from endpoint (#15844)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2025-12-26 23:38:03 +08:00 |
|
|
Mick
|
8dc6f0fc4d
|
[diffusion] refactor: centralize hardware platform detection and streamline environment variable management (#15842)
|
2025-12-26 22:16:18 +08:00 |
|
|
Mick
|
a355911909
|
[diffusion] improve: improve post-processing by moving compute-intensive tasks to GPU (#15822)
|
2025-12-26 01:29:04 +08:00 |
|
|
Mick
|
2a8a785634
|
[diffusion] log: avoid logging in hot path if unnecessary (#15818)
|
2025-12-25 18:42:52 +08:00 |
|
|
Mick
|
2c5679f314
|
[diffusion] refactor: unify the profiling api for all executors (#15718)
|
2025-12-24 23:26:09 +08:00 |
|
|
Mick
|
dfb5357448
|
[diffusion] http-server: relax openai image endpoint's strict content_type limit (#15717)
|
2025-12-24 13:26:13 +08:00 |
|
|
Mick
|
1ed946680a
|
[diffusion] bench: improve bench_serving by adding more controlling args (#15554)
|
2025-12-21 13:37:45 +08:00 |
|
|
Mick
|
d7fbe73bf2
|
[diffusion] chore: minor improvements and typo-fixing (#15556)
|
2025-12-21 13:37:10 +08:00 |
|
|
Mick
|
bc18cb8631
|
[diffusion] refactor: change zmq socket type to router for scheduler (#15479)
|
2025-12-21 00:39:54 +08:00 |
|
|
Mick
|
41bd76e18b
|
[diffusion] log: fix wrong use of suppress_other_loggers (#15534)
|
2025-12-20 23:43:55 +08:00 |
|
|
Mick
|
c6ca1b3afc
|
[diffusion] chore: allow all attention backends if not specified (#15530)
|
2025-12-20 23:14:55 +08:00 |
|