Spaces:
Runtime error
Runtime error
| // | |
| // logging | |
| // | |
| LLAMA_ATTRIBUTE_FORMAT(2, 3) | |
| void llama_log_internal (ggml_log_level level, const char * format, ...); | |
| void llama_log_callback_default(ggml_log_level level, const char * text, void * user_data); | |
| // | |
| // helpers | |
| // | |
| template <typename T> | |
| struct no_init { | |
| T value; | |
| no_init() = default; | |
| }; | |
| template <typename dst_t, typename src_t> | |
| static inline dst_t llama_cast(src_t v) { | |
| if constexpr (std::is_same_v<src_t, dst_t>) { | |
| return v; | |
| } else if constexpr (std::is_same_v<src_t, ggml_fp16_t> && std::is_same_v<dst_t, float>) { | |
| return ggml_fp16_to_fp32(v); | |
| } else if constexpr (std::is_same_v<src_t, float> && std::is_same_v<dst_t, ggml_fp16_t>) { | |
| return ggml_fp32_to_fp16(v); | |
| } else { | |
| static_assert(std::is_same_v<dst_t, void>, "unsupported type combination"); | |
| } | |
| } | |
| static inline ggml_tensor * llama_mul_mat_hadamard( | |
| ggml_context * ctx, | |
| ggml_tensor * cur, | |
| ggml_tensor * rot) { | |
| const auto n = rot->ne[0]; | |
| ggml_tensor * res; | |
| if (!ggml_is_contiguous(cur)) { | |
| res = ggml_cont_2d(ctx, cur, n, ggml_nelements(cur)/n); | |
| } else { | |
| res = ggml_reshape_2d(ctx, cur, n, ggml_nelements(cur)/n); | |
| } | |
| res = ggml_mul_mat(ctx, rot, res); | |
| ggml_mul_mat_set_hint(res, GGML_HINT_SRC0_IS_HADAMARD); | |
| res = ggml_reshape_4d(ctx, res, cur->ne[0], cur->ne[1], cur->ne[2], cur->ne[3]); | |
| return res; | |
| } | |
| struct time_meas { | |
| time_meas(int64_t & t_acc, bool disable = false); | |
| ~time_meas(); | |
| const int64_t t_start_us; | |
| int64_t & t_acc; | |
| }; | |
| template <typename T> | |
| struct buffer_view { | |
| T * data; | |
| size_t size = 0; | |
| bool has_data() const { | |
| return data && size > 0; | |
| } | |
| }; | |
| void replace_all(std::string & s, const std::string & search, const std::string & replace); | |
| // TODO: rename to llama_format ? | |
| LLAMA_ATTRIBUTE_FORMAT(1, 2) | |
| std::string format(const char * fmt, ...); | |
| 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); | |