diff --git a/aiter/ops/mha.py b/aiter/ops/mha.py
index 5c9db14959a..7e0379e2853 100644
--- a/aiter/ops/mha.py
+++ b/aiter/ops/mha.py
@@ -1293,7 +1293,7 @@ def _flash_attn_forward(
     swa = (window_size_left > 0) or (window_size_right > 0)
 
     def is_fmha_v3_fp8():
-        ret = get_gfx() == "gfx942"
+        ret = get_gfx() in ("gfx942", "gfx950")
         ret = ret and (hdim_q == 128)
         ret = ret and (q.dtype == dtypes.fp8)
         ret = ret and (
@@ -1319,6 +1319,11 @@ def can_impl_fmha_v3_fwd():
         ret = ret and (not swa)
         ret = ret and (q.dtype == dtypes.bf16 or is_fmha_v3_fp8())
         ret = ret and (cu_seqlens_q is None and cu_seqlens_kv is None)
+        # FP8 ASM kernels assemble the GQA-shift from a fixed log2 table
+        # (1,2,4,8,16); arbitrary divisor ratios route to CK.
+        if is_fmha_v3_fp8():
+            gqa_ratio = nhead_q // nhead_k
+            ret = ret and ((gqa_ratio & (gqa_ratio - 1)) == 0)
         return ret
 
     q, k, v = [maybe_contiguous(x) for x in (q, k, v)]
@@ -2074,7 +2079,7 @@ def _flash_attn_varlen_forward(
     swa = (window_size_left > 0) or (window_size_right > 0)
 
     def is_fmha_v3_fp8():
-        ret = get_gfx() == "gfx942"
+        ret = get_gfx() in ("gfx942", "gfx950")
         ret = ret and (hdim_q == 128)
         ret = ret and (q.dtype == dtypes.fp8)
         ret = ret and (
@@ -2100,6 +2105,11 @@ def can_impl_fmha_v3_fwd():
         ret = ret and (not swa)
         ret = ret and (q.dtype == dtypes.bf16 or is_fmha_v3_fp8())
         ret = ret and logits_soft_cap == 0.0
+        # FP8 ASM kernels assemble the GQA-shift from a fixed log2 table
+        # (1,2,4,8,16); arbitrary divisor ratios route to CK.
+        if is_fmha_v3_fp8():
+            gqa_ratio = nhead_q // nhead_k
+            ret = ret and ((gqa_ratio & (gqa_ratio - 1)) == 0)
         return ret
 
     q, k, v = [maybe_contiguous(x) for x in (q, k, v)]
diff --git a/csrc/cpp_itfs/mha_fwd.cu b/csrc/cpp_itfs/mha_fwd.cu
index be7f94b8486..1673fa6a05b 100644
--- a/csrc/cpp_itfs/mha_fwd.cu
+++ b/csrc/cpp_itfs/mha_fwd.cu
@@ -183,6 +183,10 @@ std::tuple<int, int, int> get_grid_dim(const mha_fwd_args& a, int ts_qo, const s
     {
         tg_div = 1; // do not merge the head and tail in seqlen_q direction
     }
+    if(arch_id == "gfx950")
+    {
+        tg_div = 1; // v2 asm kernel processes one Q tile per workgroup
+    }
     // batch
     int gdx = ((a.seqlen_q + ts_qo - 1) / ts_qo + tg_div - 1) / tg_div;
     int gdy = a.nhead_q;
diff --git a/hsa/gfx950/fmha_v3_fwd/fmha_fwd.csv b/hsa/gfx950/fmha_v3_fwd/fmha_fwd.csv
index cabc8f8b274..f418e10cd0f 100644
--- a/hsa/gfx950/fmha_v3_fwd/fmha_fwd.csv
+++ b/hsa/gfx950/fmha_v3_fwd/fmha_fwd.csv
@@ -6,4 +6,8 @@ bf16,128,128,2,1,0,256,64,_ZN5aiter32fmha_fwd_hd128_bf16_causal_groupE,fwd_hd128
 bf16,192,128,0,0,0,128,128,_ZN5aiter25fmha_fwd_hd192_hd128_bf16E,fwd_hd192_hd128_bf16.co
 bf16,192,128,2,0,0,128,128,_ZN5aiter32fmha_fwd_hd192_hd128_bf16_causalE,fwd_hd192_hd128_bf16_causal.co
 bf16,192,128,0,1,0,128,128,_ZN5aiter31fmha_fwd_hd192_hd128_bf16_groupE,fwd_hd192_hd128_bf16_group.co
-bf16,192,128,2,1,0,128,128,_ZN5aiter38fmha_fwd_hd192_hd128_bf16_causal_groupE,fwd_hd192_hd128_bf16_causal_group.co
\ No newline at end of file
+bf16,192,128,2,1,0,128,128,_ZN5aiter38fmha_fwd_hd192_hd128_bf16_causal_groupE,fwd_hd192_hd128_bf16_causal_group.co
+fp8bf16,128,128,0,0,0,256,128,_ZN5aiter24fmha_fwd_hd128_fp8_gfx950E,fwd_hd128_fp8.co
+fp8bf16,128,128,2,0,0,256,128,_ZN5aiter31fmha_fwd_hd128_fp8_causal_gfx950E,fwd_hd128_fp8_causal.co
+fp8bf16,128,128,0,1,0,256,128,_ZN5aiter30fmha_fwd_hd128_fp8_group_gfx950E,fwd_hd128_fp8_group.co
+fp8bf16,128,128,2,1,0,256,128,_ZN5aiter37fmha_fwd_hd128_fp8_causal_group_gfx950E,fwd_hd128_fp8_causal_group.co
\ No newline at end of file
diff --git a/hsa/gfx950/fmha_v3_fwd/fwd_hd128_fp8.co b/hsa/gfx950/fmha_v3_fwd/fwd_hd128_fp8.co
new file mode 100755
index 00000000000..50cf62c3d25
Binary files /dev/null and b/hsa/gfx950/fmha_v3_fwd/fwd_hd128_fp8.co differ
diff --git a/hsa/gfx950/fmha_v3_fwd/fwd_hd128_fp8_causal.co b/hsa/gfx950/fmha_v3_fwd/fwd_hd128_fp8_causal.co
new file mode 100755
index 00000000000..1c7b59f8d57
Binary files /dev/null and b/hsa/gfx950/fmha_v3_fwd/fwd_hd128_fp8_causal.co differ
diff --git a/hsa/gfx950/fmha_v3_fwd/fwd_hd128_fp8_causal_group.co b/hsa/gfx950/fmha_v3_fwd/fwd_hd128_fp8_causal_group.co
new file mode 100755
index 00000000000..2c5efb49315
Binary files /dev/null and b/hsa/gfx950/fmha_v3_fwd/fwd_hd128_fp8_causal_group.co differ
diff --git a/hsa/gfx950/fmha_v3_fwd/fwd_hd128_fp8_group.co b/hsa/gfx950/fmha_v3_fwd/fwd_hd128_fp8_group.co
new file mode 100755
index 00000000000..90122e1840b
Binary files /dev/null and b/hsa/gfx950/fmha_v3_fwd/fwd_hd128_fp8_group.co differ