[FFPA] fix some macro typos (#21)

* Update faster_prefill_attn_F16F16F16F16_L1.cu * Update faster_prefill_attn_F32F16F16F32_L1.cu
DefTruth · Jan 9, 2025 · e1b3bbc · e1b3bbc
1 parent 7469308
commit e1b3bbc
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 4 deletions.
diff --git a/csrc/cuffpa/faster_prefill_attn_F16F16F16F16_L1.cu b/csrc/cuffpa/faster_prefill_attn_F16F16F16F16_L1.cu
@@ -450,7 +450,7 @@ void ffpa_mma_acc_f16_L1(torch::Tensor Q,
   }
 
 #else
-#ifdef ENBALE_FFPA_ALL_HEADDIM
+#ifdef ENABLE_FFPA_ALL_HEADDIM
   // multiple of 32
 #define DISPATCH_KERNEL_F16_L1_HEADDIM(S)    \
   {                                          \
@@ -523,7 +523,7 @@ void ffpa_mma_acc_f16_L1(torch::Tensor Q,
 
 #endif
 
-#ifdef ENBALE_FFPA_ALL_STAGES
+#ifdef ENABLE_FFPA_ALL_STAGES
   // dispatch stages
   if (stages == 2) {
     DISPATCH_KERNEL_F16_L1_HEADDIM(2);

diff --git a/csrc/cuffpa/faster_prefill_attn_F32F16F16F32_L1.cu b/csrc/cuffpa/faster_prefill_attn_F32F16F16F32_L1.cu
@@ -452,7 +452,7 @@ void ffpa_mma_acc_f32_L1(torch::Tensor Q,
   }
 
 #else 
-#ifdef ENBALE_FFPA_ALL_HEADDIM
+#ifdef ENABLE_FFPA_ALL_HEADDIM
   // multiple of 32
 #define DISPATCH_KERNEL_F32_L1_HEADDIM(S)    \
   {                                          \
@@ -525,7 +525,7 @@ void ffpa_mma_acc_f32_L1(torch::Tensor Q,
 
 #endif
 
-#ifdef ENBALE_FFPA_ALL_STAGES
+#ifdef ENABLE_FFPA_ALL_STAGES
   // dispatch stages
   if (stages == 2) {
     DISPATCH_KERNEL_F32_L1_HEADDIM(2);