mirror of
https://github.com/zenlm/engine.git
synced 2026-10-30 15:00:05 +00:00
Guoqing BaoandGitHub
a35fcbb513
* Split Marlin and Paged Attention kernels for faster build * Typo fix
12 lines
526 B
Plaintext
12 lines
526 B
Plaintext
#include "marlin_kernel.cuh"
|
|
|
|
extern "C" void marlin_gptq_4bit_bf16(const void *A, const void *B,
|
|
void *scales, void *zeros, void *C,
|
|
int prob_m, int prob_k, int prob_n,
|
|
void *workspace, int groupsize,
|
|
int64_t stream) {
|
|
marlin_matmul<nv_bfloat16, ScalarTypeID::kU4B8, false, 4>(
|
|
A, B, scales, zeros, C, prob_m, prob_k, prob_n, workspace, groupsize,
|
|
stream);
|
|
}
|