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

[docs] fix note formatting in sglang-d documentation (#35761)

Browse Source
This commit is contained in:
Yihao Wang
2026-08-20 16:39:39 -07:00
committed by GitHub
parent 1a138e13b9
commit ba8e601358
2 changed files with 12 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/docs/sglang-diffusion/api/openai_api.mdx
+9 -7
View File
@@ -369,19 +369,21 @@ curl -X POST http://localhost:30010/v1/set_lora \
}'
```
> [!NOTE]
> When using multiple LoRAs:
> - All list parameters (`lora_nickname`, `lora_path`, `target`, `strength`) must have the same length
> - If `target` or `strength` is a single value, it will be applied to all LoRAs
> - Multiple LoRAs applied to the same target are applied in order
<Note>
When using multiple LoRAs:
- All list parameters (`lora_nickname`, `lora_path`, `target`, `strength`) must have the same length
- If `target` or `strength` is a single value, it will be applied to all LoRAs
- Multiple LoRAs applied to the same target are applied in order
</Note>
**Merge LoRA Weights**
Manually merges the currently set LoRA weights into the base model.
> [!NOTE]
> With FSDP-sharded weights, manual merge may require a full-gather and can OOM. Use `set_lora` with `merge_mode="auto"` or `"dynamic"` for the lower-peak path.
<Note>
With FSDP-sharded weights, manual merge may require a full-gather and can OOM. Use `set_lora` with `merge_mode="auto"` or `"dynamic"` for the lower-peak path.
</Note>
**Endpoint:** `POST /v1/merge_lora_weights`
docs/docs/sglang-diffusion/deployment_cookbook.mdx
+3 -2
View File
@@ -146,8 +146,9 @@ When `torch.compile` is enabled, `--offload-during-compile` stays on by default.
Breakable CUDA graph is a separate manual opt-in for supported image pipelines. If you enable `--enable-breakable-cuda-graph`, declare every served resolution in `--warmup-resolutions` so warmup captures matching graph signatures.
> [!NOTE]
> The preset is intentionally coarse. A future continuous value such as `0.0` to `1.0` could express the speed-memory tradeoff more precisely, but it would need model-specific memory models and clearer user expectations. Until then, use the preset plus explicit flags for overrides.
<Note>
The preset is intentionally coarse. A future continuous value such as `0.0` to `1.0` could express the speed-memory tradeoff more precisely, but it would need model-specific memory models and clearer user expectations. Until then, use the preset plus explicit flags for overrides.
</Note>
Examples: