diff options
| author | Carolinabanana <140120812+Carolinabanana@users.noreply.github.com> | 2024-04-09 09:16:13 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-04-09 11:16:13 +0300 |
| commit | 5dc9dd7152dedc6046b646855585bd070c91e8c8 (patch) | |
| tree | d2bae3652d91cdd9327e28fa85d167a67e050c53 /ggml.h | |
| parent | e11a8999b5690f810c2c99c14347f0834e68c524 (diff) | |
llama : add Command R Plus support (#6491)
* Add Command R Plus GGUF
* Add Command R Plus GGUF
* Loading works up to LayerNorm2D
* Export new tensors in 1D so they are not quantized.
* Fix embedding layer based on Noeda's example
* Whitespace
* Add line
* Fix unexpected tokens on MPS. Re-add F16 fix. ((Noeda)
* dranger003: Fix block index overflow in CUDA dequantizing.
* Reverted blocked multiplication code as it still has issues and could affect other Llama arches
* export norms as f32
* fix overflow issues during quant and other cleanup
* Type convention
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* dranger003: Fix more int overflow during quant.
---------
Co-authored-by: S <seast@Ss-Mac-Studio.local>
Co-authored-by: S <s@example.com>
Co-authored-by: slaren <slarengh@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'ggml.h')
| -rw-r--r-- | ggml.h | 14 |
1 files changed, 7 insertions, 7 deletions
@@ -332,8 +332,8 @@ extern "C" { GGML_API float ggml_fp16_to_fp32(ggml_fp16_t x); GGML_API ggml_fp16_t ggml_fp32_to_fp16(float x); - GGML_API void ggml_fp16_to_fp32_row(const ggml_fp16_t * x, float * y, int n); - GGML_API void ggml_fp32_to_fp16_row(const float * x, ggml_fp16_t * y, int n); + GGML_API void ggml_fp16_to_fp32_row(const ggml_fp16_t * x, float * y, int64_t n); + GGML_API void ggml_fp32_to_fp16_row(const float * x, ggml_fp16_t * y, int64_t n); struct ggml_object; struct ggml_context; @@ -2210,9 +2210,9 @@ extern "C" { enum ggml_type type, const float * src, void * dst, - int start, - int nrows, - int n_per_row, + int64_t start, + int64_t nrows, + int64_t n_per_row, const float * imatrix); // @@ -2377,8 +2377,8 @@ extern "C" { #else #define GGML_RESTRICT restrict #endif - typedef void (*ggml_to_float_t) (const void * GGML_RESTRICT x, float * GGML_RESTRICT y, int k); - typedef void (*ggml_from_float_t)(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k); + typedef void (*ggml_to_float_t) (const void * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k); + typedef void (*ggml_from_float_t)(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); typedef void (*ggml_vec_dot_t) (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT x, size_t bx, const void * GGML_RESTRICT y, size_t by, int nrc); |