Improve overlap scheduling for better TTFT (#11856)

Co-authored-by: Peng Wang <peng_wang@linux.alibaba.com>
This commit is contained in:
vipwangerxiao
2025-11-12 11:24:04 +08:00
committed by GitHub
co-authored by Peng Wang
parent 28b8c5792d
commit 8f01a12d43
3 changed files with 23 additions and 3 deletions
+1
View File
@@ -29,6 +29,7 @@ SGLang supports various environment variables that can be used to configure its
| `SGLANG_SKIP_P2P_CHECK` | Skip P2P (peer-to-peer) access check | `false` |
| `SGL_CHUNKED_PREFIX_CACHE_THRESHOLD` | Sets the threshold for enabling chunked prefix caching | `8192` |
| `SGLANG_FUSED_MLA_ENABLE_ROPE_FUSION` | Enable RoPE fusion in Fused Multi-Layer Attention | `1` |
| `SGLANG_DISABLE_CONSECUTIVE_PREFILL_OVERLAP` | Disable overlap schedule for consecutive prefill batches | `false` |
| `SGLANG_DISABLE_FA4_WARMUP` | Disable Flash Attention 4 warmup passes (set to `1`, `true`, `yes`, or `on` to disable) | `false` |
## DeepGEMM Configuration (Advanced Optimization)