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

Merge branch 'master' into gg/flash-attn

Browse source
This commit is contained in:
Georgi Gerganov 2024-04-19 14:03:55 +03:00
commit 1db66c1dac
No known key found for this signature in database
GPG key ID: BF970631944C16B7
23 changed files with 1476 additions and 830 deletions
Download patch file Download diff file Expand all files Collapse all files

6
ggml.h
View file

@ -1162,13 +1162,11 @@ extern "C" {
enum ggml_prec prec);
// indirect matrix multiplication
// ggml_mul_mat_id(ctx, as, ids, id, b) ~= ggml_mul_mat(as[ids[id]], b)
GGML_API struct ggml_tensor * ggml_mul_mat_id(
struct ggml_context * ctx,
struct ggml_tensor * as,
struct ggml_tensor * ids,
int id,
struct ggml_tensor * b);
struct ggml_tensor * b,
struct ggml_tensor * ids);
// A: m columns, n rows,
// B: p columns, n rows,