biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CPU] Add head sizes 80 and 112 with vec16 fallback (#31968)

Browse Source 
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>
This commit is contained in:
R3hankhan
2026-01-09 19:44:46 +05:30
committed by GitHub
parent 7cdf7e2fe0
commit 8e27663b6a
4 changed files with 12 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
csrc/cpu/cpu_attn_neon.hpp
View File

@@ -264,7 +264,7 @@ class AttentionImpl<ISA::NEON, scalar_t, head_dim> {
constexpr static ISA ISAType = ISA::NEON;
constexpr static bool scale_on_logits = false; // apply scale on q_buffer
static_assert(HeadDim % HeadDimAlignment == 0);
// static_assert(HeadDim % HeadDimAlignment == 0);
// the gemm micro kernel is Mx8
static_assert(HeadDimAlignment % 8 == 0);
static_assert(BlockSizeAlignment % 8 == 0);