Skip to content

GitLab

Unverified Commit 8d99a8f5 authored by pengcheng888's avatar pengcheng888 Committed by GitHub
Browse files

Merge pull request #1051 from InfiniTensor/issue/1050 

issue/1050 - fix paged caching and paged prefill on metax
parents 3e5cad10 9a0f2505
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 73 additions and 73 deletions
src/infiniop/ops/paged_caching/metax/paged_caching_metax.maca
View file @ 8d99a8f5
...@@ -12,7 +12,7 @@ INFINIOP_METAX_KERNEL pagedCaching( ...@@ -12,7 +12,7 @@ INFINIOP_METAX_KERNEL pagedCaching(
const ptrdiff_t k_src_stride, const ptrdiff_t v_src_stride, const ptrdiff_t k_src_stride, const ptrdiff_t v_src_stride,
const ptrdiff_t k_cache_block_stride, const ptrdiff_t v_cache_block_stride, const ptrdiff_t k_cache_block_stride, const ptrdiff_t v_cache_block_stride,
const ptrdiff_t k_cache_head_stride, const ptrdiff_t v_cache_head_stride, const ptrdiff_t k_cache_head_stride, const ptrdiff_t v_cache_head_stride,
const ptrdiff_t k_cache_slot_stride, const ptrdiff_t v_cache_slot_strid) { const ptrdiff_t k_cache_slot_stride, const ptrdiff_t v_cache_slot_stride) {
op::paged_caching::cuda::pagedCachingKernel<Tdata, NUM_THREADS>( op::paged_caching::cuda::pagedCachingKernel<Tdata, NUM_THREADS>(
k_cache, v_cache, k, v, slot_mapping, head_size, k_cache, v_cache, k, v, slot_mapping, head_size,
block_size, k_src_stride, v_src_stride, block_size, k_src_stride, v_src_stride,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment