EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Fix docs for clip max new tokens (#9082)

Browse Source
This commit is contained in:
Liangsheng Yin
2025-08-11 13:15:21 -07:00
committed by GitHub
parent 0d9e89ec69
commit f9afa7dceb
4 changed files with 10 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/advanced_features/pd_disaggregation.md
View File

@@ -67,7 +67,6 @@ Please be aware that this setting will cause prefill instances to take a longer
| **`SGLANG_DISAGGREGATION_HEARTBEAT_INTERVAL`** | Interval (seconds) between health checks to prefill bootstrap servers | `5.0` |
| **`SGLANG_DISAGGREGATION_HEARTBEAT_MAX_FAILURE`** | Consecutive heartbeat failures before marking prefill server offline | `2` |
| **`SGLANG_DISAGGREGATION_WAITING_TIMEOUT`** | Timeout (seconds) for receiving KV Cache after request initialization | `300` |
| **`SGLANG_CLIP_MAX_NEW_TOKENS_ESTIMATION`** | Clip request param "max_tokens" to pre_allocate | `4096` |
If a greater mean TTFT is acceptable, you can `export SGLANG_DISAGGREGATION_WAITING_TIMEOUT=600` (10 minutes) to relax the timeout condition.

2
docs/references/environment_variables.md
View File

@@ -45,7 +45,7 @@ SGLang supports various environment variables that can be used to configure its
| Environment Variable | Description | Default Value |
| --- | --- | --- |
| `SGLANG_DEBUG_MEMORY_POOL` | Enable memory pool debugging | `false` |
| `SGLANG_CLIP_MAX_NEW_TOKENS_ESTIMATION` | Clip max new tokens estimation for memory planning | Not set |
| `SGLANG_CLIP_MAX_NEW_TOKENS_ESTIMATION` | Clip max new tokens estimation for memory planning | `4096` |
| `SGLANG_DETOKENIZER_MAX_STATES` | Maximum states for detokenizer | Default value based on system |
| `SGL_DISABLE_TP_MEMORY_INBALANCE_CHECK` | Disable checks for memory imbalance across Tensor Parallel ranks | Not set (defaults to enabled check) |