add op gated_delta_net (#20455)

2026-03-14 22:01:57 +08:00
parent 710878a7dd
commit a93c0ef0fa
6 changed files with 354 additions and 28 deletions
@@ -211,7 +211,7 @@ struct sycl_device_info {
             // number of compute units on a SYCL device.
    // size_t  smpb;               // max. shared memory per block
    size_t  smpbo;              // max. shared memory per block (with opt-in)
-    int warp_size;     // max sub_group_size of SYCL
+    int warp_size;     // WARP_SIZE(16)|WARP_32_SIZE(32)|WARP_16_SIZE(16). For Intel GPU, 16 is better in most cases. Some OP support 32 only.
    int max_wg_per_cu; // max work groups per compute unit - refer to
                       // cudaOccupancyMaxActiveBlocksPerMultiprocessor
    bool    vmm;                // virtual memory support