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

[Sparse24] [Deprecation] Remove Sparse24 CT integration and kernels (#36799)

Browse Source 
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
This commit is contained in:
Kyle Sayers
2026-03-23 16:03:29 -04:00
committed by GitHub
parent fafe76b4af
commit 38364a7e32
17 changed files with 9 additions and 2674 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
benchmarks/cutlass_benchmarks/utils.py
View File

@@ -5,8 +5,6 @@
import torch
import vllm._custom_ops as ops
def to_fp8(tensor: torch.Tensor) -> torch.Tensor:
finfo = torch.finfo(torch.float8_e4m3fn)
@@ -39,49 +37,3 @@ def make_rand_tensors(
return to_fp8(a), to_fp8(b)
raise ValueError("unsupported dtype")
def prune_to_2_4(tensor):
# Reshape tensor to [N, 4] where N is number of groups of 4
original_shape = tensor.shape
reshaped = tensor.reshape(-1, 4)
# Get indices of top 2 absolute values in each group of 4
_, indices = torch.topk(torch.abs(reshaped), k=2, dim=1)
# Create binary mask
mask = torch.zeros_like(reshaped)
mask.scatter_(dim=1, index=indices, src=torch.ones_like(indices, dtype=mask.dtype))
# Apply mask and reshape back
pruned = reshaped * mask
# Turn all -0.0 to 0.0
pruned[pruned == -0.0] = 0.0
return pruned.reshape(original_shape)
def make_rand_sparse_tensors(
dtype: torch.dtype, m: int, n: int, k: int
) -> tuple[torch.Tensor, torch.Tensor]:
a = torch.randn((m, k), device="cuda") * 5
b = torch.randn((n, k), device="cuda").t() * 5
b = prune_to_2_4(b.t()).t()
if dtype == torch.int8:
a, b = to_int8(a), to_int8(b)
elif dtype == torch.float8_e4m3fn:
a, b = to_fp8(a), to_fp8(b)
elif dtype == torch.float16:
a, b = to_fp16(a), to_fp16(b)
elif dtype == torch.bfloat16:
a, b = to_bf16(a), to_bf16(b)
else:
raise ValueError("unsupported dtype")
b_compressed, e = ops.cutlass_sparse_compress(b.t())
# Compressed B, Metadata, Original A, B
return b_compressed, e, a, b