summaryrefslogtreecommitdiff
path: root/llama.h
diff options
context:
space:
mode:
authorGeorgi Gerganov <ggerganov@gmail.com>2024-02-28 18:43:38 +0200
committerGitHub <noreply@github.com>2024-02-28 18:43:38 +0200
commit08c5ee87e4cceb603ecceac90734fcdade57311b (patch)
tree50cb0cbe4fcc738c46a4d2eab2176132a9efef68 /llama.h
parent78aacf36344df724cdca9f1e1af849b2d2519cb8 (diff)
llama : remove deprecated API (#5770)
ggml-ci
Diffstat (limited to 'llama.h')
-rw-r--r--llama.h45
1 files changed, 0 insertions, 45 deletions
diff --git a/llama.h b/llama.h
index 16e28e91..a6823bb2 100644
--- a/llama.h
+++ b/llama.h
@@ -364,9 +364,6 @@ extern "C" {
LLAMA_API bool llama_supports_mlock (void);
LLAMA_API bool llama_supports_gpu_offload(void);
- LLAMA_API DEPRECATED(bool llama_mmap_supported (void), "use llama_supports_mmap() instead");
- LLAMA_API DEPRECATED(bool llama_mlock_supported(void), "use llama_supports_mlock() instead");
-
LLAMA_API const struct llama_model * llama_get_model(const struct llama_context * ctx);
LLAMA_API uint32_t llama_n_ctx (const struct llama_context * ctx);
@@ -423,14 +420,6 @@ extern "C" {
// The model needs to be reloaded before applying a new adapter, otherwise the adapter
// will be applied on top of the previous one
// Returns 0 on success
- LLAMA_API DEPRECATED(int32_t llama_apply_lora_from_file(
- struct llama_context * ctx,
- const char * path_lora,
- float scale,
- const char * path_base_model,
- int32_t n_threads),
- "use llama_model_apply_lora_from_file instead");
-
LLAMA_API int32_t llama_model_apply_lora_from_file(
const struct llama_model * model,
const char * path_lora,
@@ -606,27 +595,6 @@ extern "C" {
// Decoding
//
- // Run the llama inference to obtain the logits and probabilities for the next token(s).
- // tokens + n_tokens is the provided batch of new tokens to process
- // n_past is the number of tokens to use from previous eval calls
- // Returns 0 on success
- // DEPRECATED: use llama_decode() instead
- LLAMA_API DEPRECATED(int llama_eval(
- struct llama_context * ctx,
- llama_token * tokens,
- int32_t n_tokens,
- int32_t n_past),
- "use llama_decode() instead");
-
- // Same as llama_eval, but use float matrix input directly.
- // DEPRECATED: use llama_decode() instead
- LLAMA_API DEPRECATED(int llama_eval_embd(
- struct llama_context * ctx,
- float * embd,
- int32_t n_tokens,
- int32_t n_past),
- "use llama_decode() instead");
-
// Return batch for single sequence of tokens starting at pos_0
//
// NOTE: this is a helper function to facilitate transition to the new batch API - avoid using it
@@ -800,13 +768,6 @@ extern "C" {
float * logits_guidance,
float scale);
- LLAMA_API DEPRECATED(void llama_sample_classifier_free_guidance(
- struct llama_context * ctx,
- llama_token_data_array * candidates,
- struct llama_context * guidance_ctx,
- float scale),
- "use llama_sample_apply_guidance() instead");
-
/// @details Sorts candidate tokens by their logits in descending order and calculate probabilities based on logits.
LLAMA_API void llama_sample_softmax(
struct llama_context * ctx,
@@ -860,12 +821,6 @@ extern "C" {
llama_token_data_array * candidates,
float temp);
- LLAMA_API DEPRECATED(void llama_sample_temperature(
- struct llama_context * ctx,
- llama_token_data_array * candidates,
- float temp),
- "use llama_sample_temp instead");
-
/// @details Apply constraints from grammar
LLAMA_API void llama_sample_grammar(
struct llama_context * ctx,