CUDA: add fp kernel for larger batch size MoE (#16512)

* CUDA: kernel for larger batch sizes for MoE * WIP * WIP * WIP * WIP * WIP * WIP * fixup * tests * Move mmq_ids_helper to mmid * cleanup * Remove redundant checks
2025-10-14 13:15:15 +02:00
parent 5b6913c47b
commit 48e2fa9fb7
6 changed files with 535 additions and 204 deletions
@@ -0,0 +1,5 @@
+#pragma once
+
+void ggml_cuda_launch_mm_ids_helper(
+        const int32_t * ids, int32_t * ids_src1, int32_t * ids_dst, int32_t * expert_bounds,
+        int n_experts, int n_tokens, int n_expert_used, int nchannels_y, int si1, int sis1, cudaStream_t stream);