minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[diffusion] chore: retire released warmup and decoder flags (#33850)

Browse Source
This commit is contained in:
Mick
2026-08-06 23:02:32 +08:00
committed by GitHub
parent 591cfb0881
commit c212a6938c
19 changed files with 145 additions and 306 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/cookbook/diffusion/SANA-WM/SANA-WM.mdx
+1 -1
View File
@@ -207,7 +207,7 @@ Notes on launch behavior:
- **CPU offload flags are optional.** `--dit-cpu-offload`, `--text-encoder-cpu-offload`, and `--image-encoder-cpu-offload` are available; defaults are auto-adjusted from GPU memory (GPUs under 30 GB get more aggressive offloading).
- **Multi-GPU realtime.** Prefer explicit sequence parallelism (`--sp-degree` equal to the number of GPUs for a single session). Do not enable CFG parallel for the realtime profile: the default realtime request uses `guidance_scale=1.0`, while CFG parallel requires active cond/uncond branches.
- **FSDP.** Use `--use-fsdp-inference` only when you specifically need weight sharding for memory. For the low-latency realtime profile, prefer keeping components resident and using SP first.
- **Warmup.** Server warmup is **automatically skipped** for the realtime pipeline — a synthetic warmup request has no WebSocket session, so the server detects the registered realtime adapter and skips it. No `--warmup` flag is needed.
- **Warmup.** Server warmup is **automatically skipped** for the realtime pipeline — a synthetic warmup request has no WebSocket session, so the server detects the registered realtime adapter and skips it. No explicit `--warmup-mode` setting is needed.
Once up, the realtime WebSocket endpoint lives at `ws://127.0.0.1:30000/v1/realtime_video/generate` (use the Python client in §7 to connect — plain `curl` does not speak the `ws://` upgrade).