chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Add new moe wna16 marlin gemm (#14122)

Browse Source
This commit is contained in:
Xiaoyu Zhang
2025-12-01 23:07:53 +08:00
committed by GitHub
parent 2e8f54e61e
commit 3de09aadbc
15 changed files with 823 additions and 876 deletions
Download Patch File Download Diff File Expand all files Collapse all files
sgl-kernel/include/scalar_type.hpp
+1
View File
@@ -301,6 +301,7 @@ static inline constexpr auto kU8B128 = ScalarType::uint(8, 128);
static inline constexpr auto kFE2M1f = ScalarType::float_(2, 1, true, ScalarType::NAN_NONE);
static inline constexpr auto kFE3M2f = ScalarType::float_(3, 2, true, ScalarType::NAN_NONE);
static inline constexpr auto kFE4M3fn = ScalarType::float_(4, 3, true, ScalarType::NAN_EXTD_RANGE_MAX_MIN);
static inline constexpr auto kFE8M0fnu = ScalarType(8, 0, false, 0, true, ScalarType::NAN_EXTD_RANGE_MAX_MIN);
static inline constexpr auto kFE5M2 = ScalarType::float_IEEE754(5, 2);
static inline constexpr auto kFE8M7 = ScalarType::float_IEEE754(8, 7);
static inline constexpr auto kFE5M10 = ScalarType::float_IEEE754(5, 10);
sgl-kernel/include/sgl_kernel_ops.h
+2
View File
@@ -459,7 +459,9 @@ torch::Tensor moe_wna16_marlin_gemm(
torch::Tensor& a,
std::optional<torch::Tensor> const& c_or_none,
torch::Tensor& b_q_weight,
std::optional<torch::Tensor> const& b_bias_or_none,
torch::Tensor& b_scales,
std::optional<torch::Tensor> const& global_scale_or_none,
std::optional<torch::Tensor> const& b_zeros_or_none,
std::optional<torch::Tensor> const& g_idx_or_none,
std::optional<torch::Tensor> const& perm_or_none,