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

DP: support piggyback server load report (#11469)

Browse Source 
Signed-off-by: Chang Huaixin (OpenAnolis) <changhuaixin@linux.alibaba.com>
This commit is contained in:
Huaixin Chang
2025-12-25 11:35:05 +08:00
committed by GitHub
parent 45adad37d0
commit 0c39730b18
10 changed files with 86 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/references/environment_variables.md
+1
View File
@@ -32,6 +32,7 @@ SGLang supports various environment variables that can be used to configure its
| `SGLANG_DISABLE_CONSECUTIVE_PREFILL_OVERLAP` | Disable overlap schedule for consecutive prefill batches | `false` |
| `SGLANG_SCHEDULER_MAX_RECV_PER_POLL` | Set the maximum number of requests per poll, with a negative value indicating no limit | `-1` |
| `SGLANG_DISABLE_FA4_WARMUP` | Disable Flash Attention 4 warmup passes (set to `1`, `true`, `yes`, or `on` to disable) | `false` |
| `SGLANG_DATA_PARALLEL_BUDGET_INTERVAL` | Interval for DPBudget updates | `1` |
| `SGLANG_SCHEDULER_RECV_SKIPPER_WEIGHT_DEFAULT` | Default weight value for scheduler recv skipper counter (used when forward mode doesn't match specific modes). Only active when `--scheduler-recv-interval > 1`. The counter accumulates weights and triggers request polling when reaching the interval threshold. | `1000` |
| `SGLANG_SCHEDULER_RECV_SKIPPER_WEIGHT_DECODE` | Weight increment for decode forward mode in scheduler recv skipper. Works with `--scheduler-recv-interval` to control polling frequency during decode phase. | `1` |
| `SGLANG_SCHEDULER_RECV_SKIPPER_WEIGHT_VERIFY` | Weight increment for target verify forward mode in scheduler recv skipper. Works with `--scheduler-recv-interval` to control polling frequency during verification phase. | `1` |