anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Bugfix][BAGEL] Restore original denoise step count (#7049)

Browse Source 
Signed-off-by: Trigger <Meng.Bo.Wang@outlook.com>
Signed-off-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
This commit is contained in:
TriggerandGao Han authored and GitHub committed 2026-09-04 17:05:05 +00:00
1 parent 0f9ee6afd8
commit ea14b04e9f
12 files changed
+76 -55
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/user_guide/examples/online_serving/bagel.md
+4 -4
View File
@@ -98,10 +98,10 @@ vllm serve ByteDance-Seed/BAGEL-7B-MoT --omni --port 8091 \
--stage-overrides '{"0":{"max_num_seqs":4}}'
```
BAGEL image requests use exactly `num_inference_steps` denoising updates,
including one-step requests. The scheduler batches only requests with
compatible effective image sizes and BAGEL CFG/renormalization settings.
Sequence parallelism and diffusion cache backends such as TeaCache or
BAGEL image requests require `num_inference_steps >= 2`: the original BAGEL
schedule uses `num_inference_steps - 1` denoising updates. The scheduler batches
only requests with compatible effective image sizes and BAGEL CFG/renormalization
settings. Sequence parallelism and diffusion cache backends such as TeaCache or
Cache-DiT are not currently supported together with BAGEL step execution.
### Tensor Parallelism (TP)