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

chore: upgrade flashinfer v0.2.6.post1 jit (#6958)

Browse Source 
Co-authored-by: alcanderian <alcanderian@gmail.com>
Co-authored-by: Qiaolin Yu <qy254@cornell.edu>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
Co-authored-by: ispobock <ispobaoke@gmail.com>
This commit is contained in:
Yineng Zhang
2025-06-09 09:22:39 -07:00
committed by GitHub
parent 98c00a2df1
commit 56ccd3c22c
14 changed files with 189 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
python/sglang/srt/layers/quantization/__init__.py
View File

@@ -114,7 +114,7 @@ def get_quantization_config(quantization: str) -> Type[QuantizationConfig]:
if quantization in VLLM_QUANTIZATION_METHODS and not VLLM_AVAILABLE:
raise ValueError(
f"{quantization} quantization requires some operators from vllm. "
"Please install vllm by `pip install vllm==0.8.4`"
"Please install vllm by `pip install vllm==0.9.0.1`"
)
return QUANTIZATION_METHODS[quantization]
@@ -316,7 +316,7 @@ def monkey_patch_moe_apply(class_obj: "FusedMoEMethodBase"):
if correction_bias is not None:
if not has_correction_bias:
raise ValueError(
"Please increase the version of your vllm. Try `pip install vllm==0.8.4`"
"Please increase the version of your vllm. Try `pip install vllm==0.9.0.1`"
)
kwargs["e_score_correction_bias"] = correction_bias
return original_apply(**kwargs)