enable csgmv automatically on cuda (#13600)

2025-11-20 12:53:02 -08:00
parent 7291c72e57
commit 42028af614
2 changed files with 7 additions and 0 deletions
@@ -113,6 +113,7 @@ SGLang supports various environment variables that can be used to configure its
 | --- | --- | --- |
 | `SGLANG_WAIT_WEIGHTS_READY_TIMEOUT` | Timeout period for waiting on weights | `120` |
 | `SGLANG_DISABLE_OUTLINES_DISK_CACHE` | Disable Outlines disk cache | `true` |
+| `SGLANG_USE_CUSTOM_TRITON_KERNEL_CACHE` | Use SGLang's custom Triton kernel cache implementation for lower overheads (automatically enabled on CUDA) | `false` |

 ## Function Calling / Tool Use