[None][fix] Drop alignas(64) on MiniMax-M3 CUtensorMap members

CUtensorMap already carries its own alignment, which is stricter than
64 bytes in newer CUDA toolkits; clang-hosted nvcc rejects the weaker
alignas with "alignment cannot be set to less than the default
alignment" (SBSA build).

Signed-off-by: peihengh <259410613+peihu-nv@users.noreply.github.com>

Author: peihu-nv

cpp/tensorrt_llm/kernels/minimaxM3/attnC1.h

@@ -95,8 +95,8 @@ struct MinimaxM3AttnC1Params
     long long pf_a0, pf_b0, pf_a1, pf_b1; // mega: L2 prefetch regions issued in the attention window (bytes 0: none)
     int pf_hint;                          // 1: evict_last policy on the prefetch
     uint8_t const* wpre; // mega: optional pre-tiled QKV weight [N/128][K/128][16 KB swizzled smem image], or null
-    alignas(64) CUtensorMap wmap;   // the [2560, 6144] E4M3 weight, 128 x 128 boxes, 128-byte swizzle
-    alignas(64) CUtensorMap wmap_o; // mega: the [6144, 2048] E4M3 o_proj weight, same boxes
+    CUtensorMap wmap;    // the [2560, 6144] E4M3 weight, 128 x 128 boxes, 128-byte swizzle
+    CUtensorMap wmap_o;  // mega: the [6144, 2048] E4M3 o_proj weight, same boxes
 };
 
 //! Launch the c1 kernel on `stream`. The caller fills `params` except `wmap_o`, the o_proj weight's TMA

cpp/tensorrt_llm/kernels/minimaxM3/attnMega.h

@@ -96,8 +96,8 @@ struct MinimaxM3AttnMegaParams
     unsigned int* flags; // mega: [0, 20) tile counters (4 per call), [32 + CTA] the attention CTAs' targets
     long long pf_a0, pf_b0, pf_a1, pf_b1; // mega: L2 prefetch regions issued in the attention window (bytes 0: none)
     int pf_hint;                          // 1: evict_last policy on the prefetch
-    alignas(64) CUtensorMap wmap;         // the [2560, 6144] E4M3 weight, 128 x 128 boxes, 128-byte swizzle
-    alignas(64) CUtensorMap wmap_o;       // mega: the [6144, 2048] E4M3 o_proj weight, same boxes
+    CUtensorMap wmap;                     // the [2560, 6144] E4M3 weight, 128 x 128 boxes, 128-byte swizzle
+    CUtensorMap wmap_o;                   // mega: the [6144, 2048] E4M3 o_proj weight, same boxes
 };
 
 //! Launch the megakernel on `stream`. The caller fills `params` except `wmap`, `wmap_o`, `packed`,

cpp/tensorrt_llm/kernels/minimaxM3/fusedDecodeAttn.h

@@ -86,8 +86,8 @@ struct MinimaxM3FusedDecodeAttnParams
     long long pf_a0, pf_b0, pf_a1, pf_b1; // mega: L2 prefetch regions issued in the attention window (bytes 0: none)
     int pf_hint;                          // 1: evict_last policy on the prefetch
     uint8_t const* wpre; // mega: optional pre-tiled QKV weight [N/128][K/128][16 KB swizzled smem image], or null
-    alignas(64) CUtensorMap wmap;   // the [2560, 6144] E4M3 weight, 128 x 128 boxes, 128-byte swizzle
-    alignas(64) CUtensorMap wmap_o; // mega: the [6144, 2048] E4M3 o_proj weight, same boxes
+    CUtensorMap wmap;    // the [2560, 6144] E4M3 weight, 128 x 128 boxes, 128-byte swizzle
+    CUtensorMap wmap_o;  // mega: the [6144, 2048] E4M3 o_proj weight, same boxes
 };
 
 //! Whether the (decode_query_len, query tokens per cluster, KV blocks per CTA) geometry is compiled. The MXFP8