[Bugfix][CI] fix typos (#34934)
Signed-off-by: 1195343015 <1195343015@qq.com> Signed-off-by: Jiayi Yan <66017932+1195343015@users.noreply.github.com> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
co-authored by
Harry Mellor
parent
8c760b6ab6
commit
6a895197fa
@@ -420,7 +420,7 @@ class AttentionImpl<ISA::AMX, scalar_t, head_dim> {
|
||||
const int64_t block_size, const int64_t block_size_stride) {
|
||||
// For AMX 2D tiles, size of each line is 64 bytes
|
||||
constexpr int64_t amx_tile_row_size = AMX_TILE_ROW_BYTES;
|
||||
// For AMX B martix, N always is 16
|
||||
// For AMX B matrix, N always is 16
|
||||
constexpr int64_t amx_b_tile_n_size = AMX_TILE_ROW_BYTES / 4;
|
||||
constexpr int64_t amx_b_tile_k_size = amx_tile_row_size / sizeof(scalar_t);
|
||||
// For now suppose block_size is divisible by amx_tile_column_num
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
|
||||
#include <torch/library.h>
|
||||
|
||||
// Note: overwrite the external defination for sharing same name between
|
||||
// Note: overwrite the external definition for sharing same name between
|
||||
// libraries use different ISAs.
|
||||
#define TORCH_EXTENSION_NAME _C
|
||||
|
||||
|
||||
@@ -35,11 +35,11 @@ __global__ void batched_moe_align_block_size_kernel(
|
||||
int32_t const block_ids_size = sorted_ids_size / block_size;
|
||||
int32_t const SENTINEL =
|
||||
num_batches * max_tokens_per_batch; // To denote invalid entries.
|
||||
// Intialize sorted_ids
|
||||
// Initialize sorted_ids
|
||||
for (size_t i = threadIdx.x; i < sorted_ids_size; i += stride) {
|
||||
sorted_ids[i] = SENTINEL;
|
||||
}
|
||||
// Intialize expert_ids with -1
|
||||
// Initialize expert_ids with -1
|
||||
for (size_t i = threadIdx.x; i < block_ids_size; i += stride) {
|
||||
block_ids[i] = -1;
|
||||
}
|
||||
|
||||
@@ -542,7 +542,7 @@ __global__ void silu_mul_fp8_quant_deep_gemm_kernel(
|
||||
if (!lane_id) {
|
||||
// Store scales.
|
||||
if constexpr (std::is_same<scale_t, uint8_t>::value) {
|
||||
// Packed UE8MO format. Remove Mantissa.
|
||||
// Packed UE8M0 format. Remove Mantissa.
|
||||
*y_s_ptr = reinterpret_cast<int16_t&>(y_s) >> 7;
|
||||
|
||||
bool const jump_pack = (current_group_id + 1) % 4 == 0;
|
||||
|
||||
@@ -1476,7 +1476,7 @@ __global__ void __launch_bounds__(WvPrGrp* THRDS)
|
||||
#endif
|
||||
|
||||
// B[] staging is cooperative across GrpsShrB, so sync here before reading
|
||||
// back. This wait is currently inserted by compiler, but not gauranteed.
|
||||
// back. This wait is currently inserted by compiler, but not guaranteed.
|
||||
asm volatile("s_waitcnt 0");
|
||||
__syncthreads();
|
||||
|
||||
|
||||
Reference in New Issue
Block a user