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

CUDA full GPU acceleration, KV cache in VRAM (#1827)

Browse source 
* Fixed CUDA RoPE

* ggml_cuda_mul_mat_vec_p021

* ggml_cuda_scale

* ggml_cuda_diag_mask_inf

* ggml_is_permuted

* ggml_cuda_cpy

* flatten rows for ggml_cuda_op

* Added a --low-vram option

* Fixed Windows performance

* Fixed LLAMA_CUDA_DMMV_Y > 1 for WizardLM
This commit is contained in:
Johannes Gäßler 2023-06-14 19:47:19 +02:00 • committed by GitHub
parent 9254920265
commit 254a7a7a5f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
11 changed files with 853 additions and 149 deletions
Download patch file Download diff file Expand all files Collapse all files

6
ggml.c
View file

@ -3939,6 +3939,12 @@ bool ggml_is_contiguous(const struct ggml_tensor * tensor) {
tensor->nb[3] == tensor->nb[2]*tensor->ne[2];
}
bool ggml_is_permuted(const struct ggml_tensor * tensor) {
static_assert(GGML_MAX_DIMS == 4, "GGML_MAX_DIMS is not 4 - update this function");
return tensor->nb[0] > tensor->nb[1] || tensor->nb[1] > tensor->nb[2] || tensor->nb[2] > tensor->nb[3];
}
static inline bool ggml_is_padded_1d(const struct ggml_tensor * tensor) {
static_assert(GGML_MAX_DIMS == 4, "GGML_MAX_DIMS is not 4 - update this function");