biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI/Build] drop support for Python 3.8 EOL (#8464)

Browse Source 
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
This commit is contained in:
Aaron Pham
2024-11-06 02:11:55 -05:00
committed by GitHub
parent 4be3a45158
commit 21063c11c7
115 changed files with 239 additions and 321 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
csrc/quantization/machete/generate.py
View File

@@ -468,7 +468,7 @@ def generate():
impl_configs = []
GPTQ_kernel_type_configs = list(
(TypeConfig(
TypeConfig(
element_a=element_a,
element_b=element_b,
element_b_scale=element_a,
@@ -476,7 +476,7 @@ def generate():
element_d=element_a,
accumulator=DataType.f32,
) for element_b in (VLLMDataType.u4b8, VLLMDataType.u8b128)
for element_a in (DataType.f16, DataType.bf16)))
for element_a in (DataType.f16, DataType.bf16))
GPTQ_kernel_specializations = [
Specialization(with_C=False, with_zeropoints=False, with_scales=True)
@@ -490,7 +490,7 @@ def generate():
]
AWQ_kernel_type_configs = list(
(TypeConfig(
TypeConfig(
element_a=element_a,
element_b=element_b,
element_b_scale=element_a,
@@ -498,7 +498,7 @@ def generate():
element_d=element_a,
accumulator=DataType.f32,
) for element_b in (DataType.u4, DataType.u8)
for element_a in (DataType.f16, DataType.bf16)))
for element_a in (DataType.f16, DataType.bf16))
AWQ_kernel_specializations = [
Specialization(with_C=False, with_zeropoints=True, with_scales=True)