CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-18 11:46:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into compilade/refactor-kv-cache

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-06-08 17:30:49 -04:00
parent fee3c1d740 d4d915d351
commit 6840ac0bca
242 changed files with 83873 additions and 22119 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
ggml.h
View File

@@ -1465,7 +1465,6 @@ extern "C" {
// rotary position embedding
// if mode & 1 == 1, skip n_past elements (NOT SUPPORTED)
// if mode & 2 == 1, GPT-NeoX style
// if mode & 4 == 1, ChatGLM style
//
// b is an int32 vector with size a->ne[2], it contains the positions
// c is freq factors (e.g. phi3-128k), (optional)
@@ -1474,8 +1473,7 @@ extern "C" {
struct ggml_tensor * a,
struct ggml_tensor * b,
int n_dims,
int mode,
int n_ctx);
int mode);
// in-place, returns view(a)
GGML_API struct ggml_tensor * ggml_rope_inplace(
@@ -1483,8 +1481,7 @@ extern "C" {
struct ggml_tensor * a,
struct ggml_tensor * b,
int n_dims,
int mode,
int n_ctx);
int mode);
// custom RoPE
GGML_API struct ggml_tensor * ggml_rope_ext(
@@ -1494,8 +1491,7 @@ extern "C" {
struct ggml_tensor * c,
int n_dims,
int mode,
int n_ctx,
int n_orig_ctx,
int n_ctx_orig,
float freq_base,
float freq_scale,
float ext_factor,
@@ -1511,8 +1507,7 @@ extern "C" {
struct ggml_tensor * c,
int n_dims,
int mode,
int n_ctx,
int n_orig_ctx,
int n_ctx_orig,
float freq_base,
float freq_scale,
float ext_factor,
@@ -1526,8 +1521,7 @@ extern "C" {
struct ggml_tensor * b,
int n_dims,
int mode,
int n_ctx,
int n_orig_ctx,
int n_ctx_orig,
float freq_base,
float freq_scale,
float ext_factor,
@@ -1542,8 +1536,7 @@ extern "C" {
struct ggml_tensor * b,
int n_dims,
int mode,
int n_ctx,
int n_orig_ctx,
int n_ctx_orig,
float freq_base,
float freq_scale,
float ext_factor,
@@ -1552,17 +1545,9 @@ extern "C" {
float beta_slow),
"use ggml_rope_ext_inplace instead");
struct ggml_tensor * ggml_rope_xpos_inplace(
struct ggml_context * ctx,
struct ggml_tensor * a,
struct ggml_tensor * b,
int n_dims,
float base,
bool down);
// compute correction dims for YaRN RoPE scaling
GGML_CALL void ggml_rope_yarn_corr_dims(
int n_dims, int n_orig_ctx, float freq_base, float beta_fast, float beta_slow, float dims[2]);
int n_dims, int n_ctx_orig, float freq_base, float beta_fast, float beta_slow, float dims[2]);
// rotary position embedding backward, i.e compute dx from dy
// a - dy
@@ -1573,16 +1558,13 @@ extern "C" {
struct ggml_tensor * c,
int n_dims,
int mode,
int n_ctx,
int n_orig_ctx,
int n_ctx_orig,
float freq_base,
float freq_scale,
float ext_factor,
float attn_factor,
float beta_fast,
float beta_slow,
float xpos_base,
bool xpos_down);
float beta_slow);
// clamp
// in-place, returns view(a)
@@ -2422,7 +2404,6 @@ extern "C" {
GGML_API int ggml_cpu_has_wasm_simd (void);
GGML_API int ggml_cpu_has_blas (void);
GGML_API int ggml_cpu_has_cuda (void);
GGML_API int ggml_cpu_has_clblast (void);
GGML_API int ggml_cpu_has_vulkan (void);
GGML_API int ggml_cpu_has_kompute (void);
GGML_API int ggml_cpu_has_gpublas (void);