diff --git a/backend/cpp/turboquant/patches/0002-remove-d512-turbo-shared-mem-overflow.patch b/backend/cpp/turboquant/patches/0002-remove-d512-turbo-shared-mem-overflow.patch
new file mode 100644
index 000000000..7dfb385c3
--- /dev/null
+++ b/backend/cpp/turboquant/patches/0002-remove-d512-turbo-shared-mem-overflow.patch
@@ -0,0 +1,52 @@
+diff --git a/ggml/src/ggml-cuda/fattn-vec.cuh b/ggml/src/ggml-cuda/fattn-vec.cuh
+index 680fd12..ffd6604 100644
+--- a/ggml/src/ggml-cuda/fattn-vec.cuh
++++ b/ggml/src/ggml-cuda/fattn-vec.cuh
+@@ -980,6 +980,3 @@ extern DECL_FATTN_VEC_CASE(256, GGML_TYPE_TURBO2_0, GGML_TYPE_TURBO4_0);
+ extern DECL_FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_F16);
+ extern DECL_FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_Q8_0);
+ extern DECL_FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_BF16);
+-extern DECL_FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_TURBO3_0);
+-extern DECL_FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_TURBO2_0);
+-extern DECL_FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_TURBO4_0);
+diff --git a/ggml/src/ggml-cuda/fattn.cu b/ggml/src/ggml-cuda/fattn.cu
+index 5c614a9..d765cfc 100644
+--- a/ggml/src/ggml-cuda/fattn.cu
++++ b/ggml/src/ggml-cuda/fattn.cu
+@@ -507,9 +507,6 @@ static void ggml_cuda_flash_attn_ext_vec(ggml_backend_cuda_context & ctx, ggml_t
+     FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_F16)
+     FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_Q8_0)
+     FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_BF16)
+-    FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_TURBO3_0)
+-    FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_TURBO2_0)
+-    FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_TURBO4_0)
+ 
+ #ifdef GGML_CUDA_FA_ALL_QUANTS
+     FATTN_VEC_CASES_ALL_D(GGML_TYPE_F16,  GGML_TYPE_F16)
+diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo2_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo2_0.cu
+index a93be56..3630d87 100644
+--- a/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo2_0.cu
++++ b/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo2_0.cu
+@@ -5,4 +5,3 @@
+ DECL_FATTN_VEC_CASE( 64, GGML_TYPE_Q8_0, GGML_TYPE_TURBO2_0);
+ DECL_FATTN_VEC_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_TURBO2_0);
+ DECL_FATTN_VEC_CASE(256, GGML_TYPE_Q8_0, GGML_TYPE_TURBO2_0);
+-DECL_FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_TURBO2_0);
+diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo3_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo3_0.cu
+index 3c806c2..c8a4d9f 100644
+--- a/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo3_0.cu
++++ b/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo3_0.cu
+@@ -5,4 +5,3 @@
+ DECL_FATTN_VEC_CASE( 64, GGML_TYPE_Q8_0, GGML_TYPE_TURBO3_0);
+ DECL_FATTN_VEC_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_TURBO3_0);
+ DECL_FATTN_VEC_CASE(256, GGML_TYPE_Q8_0, GGML_TYPE_TURBO3_0);
+-DECL_FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_TURBO3_0);
+diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo4_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo4_0.cu
+index 180902f..1646ef0 100644
+--- a/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo4_0.cu
++++ b/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo4_0.cu
+@@ -5,4 +5,3 @@
+ DECL_FATTN_VEC_CASE( 64, GGML_TYPE_Q8_0, GGML_TYPE_TURBO4_0);
+ DECL_FATTN_VEC_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_TURBO4_0);
+ DECL_FATTN_VEC_CASE(256, GGML_TYPE_Q8_0, GGML_TYPE_TURBO4_0);
+-DECL_FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_TURBO4_0);
diff --git a/backend/cpp/turboquant/patches/0002-remove-d512-turbo23-shared-mem-overflow.patch b/backend/cpp/turboquant/patches/0002-remove-d512-turbo23-shared-mem-overflow.patch
deleted file mode 100644
index 12a937148..000000000
--- a/backend/cpp/turboquant/patches/0002-remove-d512-turbo23-shared-mem-overflow.patch
+++ /dev/null
@@ -1,18 +0,0 @@
-diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo2_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo2_0.cu
-index a93be56..3630d87 100644
---- a/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo2_0.cu
-+++ b/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo2_0.cu
-@@ -5,4 +5,3 @@
- DECL_FATTN_VEC_CASE( 64, GGML_TYPE_Q8_0, GGML_TYPE_TURBO2_0);
- DECL_FATTN_VEC_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_TURBO2_0);
- DECL_FATTN_VEC_CASE(256, GGML_TYPE_Q8_0, GGML_TYPE_TURBO2_0);
--DECL_FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_TURBO2_0);
-diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo3_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo3_0.cu
-index 3c806c2..c8a4d9f 100644
---- a/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo3_0.cu
-+++ b/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-turbo3_0.cu
-@@ -5,4 +5,3 @@
- DECL_FATTN_VEC_CASE( 64, GGML_TYPE_Q8_0, GGML_TYPE_TURBO3_0);
- DECL_FATTN_VEC_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_TURBO3_0);
- DECL_FATTN_VEC_CASE(256, GGML_TYPE_Q8_0, GGML_TYPE_TURBO3_0);
--DECL_FATTN_VEC_CASE_D512(GGML_TYPE_Q8_0, GGML_TYPE_TURBO3_0);