llama: refactor fused ops (#24646)

This commit is contained in:
Aman Gupta
2026-07-08 18:18:09 +08:00
committed by GitHub
parent bbebeec4a8
commit 90e0f5cfcb
6 changed files with 122 additions and 131 deletions
-4
View File
@@ -103,7 +103,3 @@ std::string llama_format_tensor_shape(const std::vector<int64_t> & ne);
std::string llama_format_tensor_shape(const struct ggml_tensor * t);
std::string gguf_kv_to_str(const struct gguf_context * ctx_gguf, int i);
#define LLAMA_TENSOR_NAME_FATTN "__fattn__"
#define LLAMA_TENSOR_NAME_FGDN_AR "__fgdn_ar__"
#define LLAMA_TENSOR_NAME_FGDN_CH "__fgdn_ch__"