chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

[dpc]: unify DP controller load balancing and simplify dispatch logic (#16258)

Browse Source
This commit is contained in:
Ratish P
2026-01-11 12:38:03 +08:00
committed by GitHub
parent cc25f9df50
commit c0248d6f37
4 changed files with 32 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/advanced_features/server_arguments.md
+1 -1
View File
@@ -205,7 +205,7 @@ Please consult the documentation below and [server_args.py](https://github.com/s
| Argument | Description | Defaults | Options |
| --- | --- | --- | --- |
| `--data-parallel-size`<br>`--dp-size` | The data parallelism size. | `1` | Type: int |
| `--load-balance-method` | The load balancing strategy for data parallelism. The Minimum Token algorithm can only be used when DP attention is applied. This algorithm performs load balancing based on the real-time token load of the DP workers. | `auto` | `auto`, `round_robin`, `follow_bootstrap_room`, `shortest_queue`, `minimum_tokens` |
| `--load-balance-method` | The load balancing strategy for data parallelism. The `total_tokens` algorithm can only be used when DP attention is applied. This algorithm performs load balancing based on the real-time token load of the DP workers. | `auto` | `auto`, `round_robin`, `follow_bootstrap_room`, `total_requests`, `total_tokens` |
| `--load-watch-interval` | The interval of load watching in seconds. | `0.1` | Type: float |
## Multi-node distributed serving
docs/platforms/ascend_npu_support_features.md
+1 -1
View File
@@ -153,7 +153,7 @@ click [Server Arguments](https://docs.sglang.io/advanced_features/server_argumen
| Argument | Defaults | Options | A2 | A3 |
|----------------------------------------|---------------|-------------------------------------------------------------|:----------------------------------------:|:----------------------------------------:|
| `--data-parallel-size`<br/>`--dp-size` | `1` | Type: int | **<span style="color: green;">√</span>** | **<span style="color: green;">√</span>** |
| `--load-balance-method` | `round_robin` | `round_robin`,<br/> `shortest_queue`,<br/> `minimum_tokens` | **<span style="color: green;">√</span>** | **<span style="color: green;">√</span>** |
| `--load-balance-method` | `round_robin` | `round_robin`,<br/> `total_requests`,<br/> `total_tokens` | **<span style="color: green;">√</span>** | **<span style="color: green;">√</span>** |
| `--prefill-round-robin-balance` | `False` | bool flag<br/> (set to enable) | **<span style="color: green;">√</span>** | **<span style="color: green;">√</span>** |
## Multi-node distributed serving