mirror of
https://github.com/zenlm/engine.git
synced 2026-10-30 15:00:05 +00:00
Eric BuehlerandGitHub
a691154bbe
* DSv3 fixes * Just save the progress * Fix launch of blockwise fp8 dequant * It actually works * Async ops * Optimize non-mla with cat * Fix non-cuda build * Update build * Add more CUDA_CHECK * Works really now * Working fully now with pagedattn * Format everything
19 lines
657 B
Plaintext
19 lines
657 B
Plaintext
#include <cassert>
|
|
|
|
extern "C" void marlin_4bit_f16(const void *A, const void *B, void *s, void *C,
|
|
int prob_m, int prob_k, int prob_n,
|
|
void *workspace, int groupsize) {
|
|
assert(false);
|
|
}
|
|
|
|
extern "C" void marlin_4bit_bf16(const void *A, const void *B, void *s, void *C,
|
|
int prob_m, int prob_k, int prob_n,
|
|
void *workspace, int groupsize) {
|
|
assert(false);
|
|
}
|
|
|
|
extern "C" void gptq_marlin_repack(void *weight, void *perm, void *out,
|
|
int size_k, int size_n, int num_bits) {
|
|
assert(false);
|
|
}
|