Commit Graph
15 Commits
Author SHA1 Message Date
Lancer 109bba8cdf [Bugfix] Treat kv_cache_dtype=auto as unset for ring attention (#3622)
Signed-off-by: Lancer <maruixiang6688@gmail.com>
2026-05-20 05:18:57 +00:00
lyj-jjjandCursor bbc00f9f86 [BugFix] fix(omni): isolate diffusion KV-cache dtype from vLLM --kv-cache-dtype #3585 (#3596)
Signed-off-by: lyj-jjj <liuyingjun5@huawei.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-15 11:22:59 +08:00
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
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
Canlin GuoandHongsheng 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
Canlin Guo 6dc61c9a20 [Perf] Skip Wan2.2 cross attn Ulysses SP (#2459)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
2026-04-03 16:23:36 +08:00
XU Mingshi ac397ae2a0 [Diffusion][Perf] Remove Redundant Communication Cost by Refining SP Hook Design (#1275)
Signed-off-by: mxuax <mxuax@connect.ust.hk>
Signed-off-by: XU Mingshi <91017482+mxuax@users.noreply.github.com>
2026-02-09 19:10:10 +08:00
dsinghvi f8dd566abd [BugFix] Fix to use correct attn backend (#1038)
Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com>
2026-01-29 21:20:39 +08:00
catcatandHongsheng Liu 026f613e57 [Misc] Merge diffusion forward context (#582)
Signed-off-by: iwzbi <wzbi@zju.edu.cn>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-01-05 22:49:03 +08:00
Canlin Guo 1c9e58ee19 [Bugfix] Removed the NPU-specific code path in _run_local_attention (#597)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
2026-01-04 14:14:10 +08:00
Yipeng Liu 4321b42e47 [BugFix] Fix repeated warnings from get_current_omni_diffusion_config outside init phase (#593)
Signed-off-by: Yipeng Liu <2206457717@qq.com>
2026-01-03 22:43:41 +08:00
680742bc33 [Diffusion]: Diffusion Ring Attention support (#273)
Signed-off-by: mxuax <mxuax@connect.ust.hk>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2025-12-31 14:26:30 +00:00
Didan DengandJiangyun Zhu ee2b78e826 [Diffusion][Bug-Fix]: Fix Ulysses SP Accurary Error (#377)
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
2025-12-22 17:48:39 +08:00
Didan Deng 85f0c1177f [Diffusion]: Diffusion Ulysses-Sequence-Parallelism support (#189)
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
2025-12-17 15:41:31 +08:00
Jiangyun ZhuandSamit 98fe15762d [Diffusion] Init Attention Backends and Selector for Diffusion (#115)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: samithuang <285365963@qq.com>
Co-authored-by: Samit <285365963@qq.com>
2025-12-05 10:46:20 +00:00