CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal : add support for non-padded FA KV (#16148)

Browse Source 
* metal : pad K, V and Mask when needed

* cont : simplify

* cuda : add TODO about KV padding requirement

* metal : add comments

* metal : remove mask padding requirement
This commit is contained in:
Georgi Gerganov
2025-10-07 08:23:30 +03:00
committed by GitHub
parent 1d6092fc72
commit 0a319bb75e
9 changed files with 460 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/test-backend-ops.cpp
View File

@@ -6773,7 +6773,8 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
if (hsk > 64 && nr3 > 1) continue; // skip broadcast for large head sizes
for (int nr2 : { 1, 4, 16 }) {
if (nr2 == 16 && hsk != 128) continue;
for (int kv : { 512, 1024, }) {
//for (int kv : { 1, 17, 31, 33, 61, 113, 65, 127, 129, 130, 255, 260, 371, 380, 407, 512, 1024, }) {
for (int kv : { 113, 512, 1024, }) {
if (nr2 != 1 && kv != 512) continue;
for (int nb : { 1, 3, 32, 35, }) {
for (ggml_prec prec : {GGML_PREC_F32, GGML_PREC_DEFAULT}) {