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

Revert "fix some typos" (#6244)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-05-12 12:53:26 -07:00
committed by GitHub
parent bad7c26fdc
commit e8e18dcdcc
95 changed files with 276 additions and 276 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
python/sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py
View File

@@ -363,7 +363,7 @@ class CompressedTensorsConfig(QuantizationConfig):
if self._is_wNa16_group_channel(weight_quant, input_quant):
if not VLLM_AVAILABLE:
raise ImportError(
"vLLM is not installed, to use CompressedTensorsW4A16Sparse24 and CompressedTensorsWNA16, please install vLLM"
"vllm is not installed, to use CompressedTensorsW4A16Sparse24 and CompressedTensorsWNA16, please install vllm"
)
if (
self.quant_format == CompressionFormat.marlin_24.value
@@ -409,7 +409,7 @@ class CompressedTensorsConfig(QuantizationConfig):
if self._is_fp8_w8a16(weight_quant, input_quant):
if not VLLM_AVAILABLE:
raise ImportError(
"vLLM is not installed, to use CompressedTensorsW8A16Fp8, please install vLLM"
"vllm is not installed, to use CompressedTensorsW8A16Fp8, please install vllm"
)
is_static_input_scheme = input_quant and not input_quant.dynamic
return CompressedTensorsW8A16Fp8(
@@ -491,7 +491,7 @@ class CompressedTensorsConfig(QuantizationConfig):
):
if not VLLM_AVAILABLE:
raise ImportError(
"vLLM is not installed, to use CompressedTensors24, please install vLLM"
"vllm is not installed, to use CompressedTensors24, please install vllm"
)
# Have a valid sparsity scheme
# Validate layer is supported by Cutlass 2:4 Kernel

2
python/sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py
View File

@@ -65,7 +65,7 @@ class CompressedTensorsMoEMethod:
if quant_config._is_wNa16_group_channel(weight_quant, input_quant):
if not VLLM_AVAILABLE:
raise ImportError(
"vLLM is not installed, to use CompressedTensorsWNA16MoEMethod, please install vLLM."
"vllm is not installed, to use CompressedTensorsWNA16MoEMethod, please install vllm."
)
return CompressedTensorsWNA16MoEMethod(quant_config)
elif quant_config._is_fp8_w8a8(weight_quant, input_quant):

6
python/sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py
View File

@@ -27,10 +27,10 @@ except ImportError:
MARLIN_FP8_AVAILABLE = False
def apply_fp8_marlin_linear(*args, **kwargs):
raise ImportError("vLLM is not installed")
raise ImportError("vllm is not installed")
def prepare_fp8_layer_for_marlin(*args, **kwargs):
raise ImportError("vLLM is not installed")
raise ImportError("vllm is not installed")
__all__ = ["CompressedTensorsW8A16Fp8"]
@@ -45,7 +45,7 @@ class CompressedTensorsW8A16Fp8(CompressedTensorsScheme):
if not MARLIN_FP8_AVAILABLE:
raise ImportError(
"vLLM is not installed. To use CompressedTensorsW8A16Fp8, please install vLLM"
"vllm is not installed. To use CompressedTensorsW8A16Fp8, please install vllm"
)
@classmethod