vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'ggerganov:master' into bitnet

Browse source
This commit is contained in:
Eddie-Wang 2024-06-10 10:51:47 +08:00 • committed by GitHub
commit 841c903ff9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
218 changed files with 5021 additions and 8134 deletions
Download patch file Download diff file Expand all files Collapse all files

37
ggml.h
View file

@ -1467,7 +1467,6 @@ 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)
@ -1476,8 +1475,7 @@ 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(
@ -1485,8 +1483,7 @@ 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(
@ -1496,8 +1493,7 @@ 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,
@ -1513,8 +1509,7 @@ 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,
@ -1528,8 +1523,7 @@ 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,
@ -1544,8 +1538,7 @@ 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,
@ -1554,17 +1547,9 @@ 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
@ -1575,16 +1560,13 @@ 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)
@ -2427,7 +2409,6 @@ 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);