vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

cuda : fix rope with partial rotation and non-cont src (#14580)

Browse source 
* cuda : fix rope non-cont

ggml-ci

* cont : fix multi-rope + add test

ggml-ci

* sycl : try fix

ggml-ci

* cont : fix sycl + clean-up cuda

ggml-ci
This commit is contained in:
Georgi Gerganov 2025-07-08 10:15:21 +03:00 • committed by GitHub
parent 75c91de6e9
commit 4d0dcd4a06
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 50 additions and 51 deletions
Download patch file Download diff file Expand all files Collapse all files

20
tests/test-backend-ops.cpp
View file

@ -5323,12 +5323,12 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
for (bool fw : {true, false}) { // fw == forward
bool all = true;
for (float v : { 0, 1 }) {
for (float fs : { 1.0f, 1.4245f }) {
for (float ef : { 0.0f, 0.7465f }) {
for (float af : { 1.0f, 1.4245f }) {
for (ggml_type type : {GGML_TYPE_F32, GGML_TYPE_F16}) {
for (bool ff : {false, true}) { // freq_factors
for (float fs : { 1.0f, 1.4245f }) {
for (float ef : { 0.0f, 0.7465f }) {
for (float af : { 1.0f, 1.4245f }) {
for (ggml_type type : {GGML_TYPE_F32, GGML_TYPE_F16}) {
for (bool ff : {false, true}) { // freq_factors
for (float v : { 0, 1 }) {
test_cases.emplace_back(new test_rope(type, {128, 32, 2, 1}, 128, 0, 512, fs, ef, af, ff, v, fw)); // llama 7B
if (all) {
@ -5341,13 +5341,21 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_rope(type, { 64, 1, 2, 1}, 64, 2, 512, fs, ef, af, ff, v, fw)); // neox (falcon 7B)
test_cases.emplace_back(new test_rope(type, { 64, 71, 2, 1}, 64, 2, 512, fs, ef, af, ff, v, fw)); // neox (falcon 7B)
test_cases.emplace_back(new test_rope(type, { 64, 8, 2, 1}, 64, 2, 512, fs, ef, af, ff, v, fw)); // neox (falcon 40B)
test_cases.emplace_back(new test_rope(type, { 80, 32, 2, 1}, 20, 0, 512, fs, ef, af, ff, v, fw));
test_cases.emplace_back(new test_rope(type, { 80, 32, 2, 1}, 32, 0, 512, fs, ef, af, ff, v, fw));
test_cases.emplace_back(new test_rope(type, { 80, 32, 4, 1}, 32, 0, 512, fs, ef, af, ff, v, fw));
test_cases.emplace_back(new test_rope(type, { 80, 32, 2, 1}, 20, 2, 512, fs, ef, af, ff, v, fw)); // neox (stablelm)
test_cases.emplace_back(new test_rope(type, { 80, 32, 2, 1}, 32, 2, 512, fs, ef, af, ff, v, fw)); // neox (phi-2)
test_cases.emplace_back(new test_rope(type, { 80, 32, 4, 1}, 32, 2, 512, fs, ef, af, ff, v, fw)); // neox (phi-2)
}
if (all) {
test_cases.emplace_back(new test_rope(type, {128, 12, 2, 1}, 128, GGML_ROPE_TYPE_MROPE, 512, fs, ef, af, ff, v, fw)); // rope_multi,m-rope (qwen2vl 2B)
test_cases.emplace_back(new test_rope(type, {128, 28, 2, 1}, 128, GGML_ROPE_TYPE_MROPE, 512, fs, ef, af, ff, v, fw)); // rope_multi,m-rope (qwen2vl 7B)
test_cases.emplace_back(new test_rope(type, {128, 12, 2, 1}, 20, GGML_ROPE_TYPE_MROPE, 512, fs, ef, af, ff, v, fw));
test_cases.emplace_back(new test_rope(type, {128, 28, 2, 1}, 32, GGML_ROPE_TYPE_MROPE, 512, fs, ef, af, ff, v, fw));
test_cases.emplace_back(new test_rope(type, { 80, 16, 2, 1}, 80, GGML_ROPE_TYPE_VISION, 512, fs, ef, af, ff, v, fw)); // rope_multi,m-rope (qwen2vl ViT)
}