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

Revert "enable csgmv automatically on cuda" (#13707)

Browse Source
This commit is contained in:
Qiaolin Yu
2025-11-21 10:37:41 -08:00
committed by GitHub
parent dab06b50ab
commit 681b9e6425
2 changed files with 0 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/references/environment_variables.md
View File

@@ -113,7 +113,6 @@ 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

6
python/sglang/srt/utils/common.py
View File

@@ -3618,12 +3618,6 @@ def cached_triton_kernel(key_fn=None):
"""
def decorator(fn):
# Auto-enable the custom kernel cache for CUDA, where it is
# known to be compatible.
if is_cuda() and not envs.SGLANG_USE_CUSTOM_TRITON_KERNEL_CACHE.is_set():
logger.debug("Detected platform CUDA, using custom triton kernel cache.")
return CachedKernel(fn, key_fn)
if envs.SGLANG_USE_CUSTOM_TRITON_KERNEL_CACHE.get():
logger.debug(
f"{envs.SGLANG_USE_CUSTOM_TRITON_KERNEL_CACHE.name} = True. Using custom triton kernel cache."