Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-27 21:46:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

hexagon: support for backend sampler (#29502)

Browse Source 
* hex-topk: trying to improve/cleanup the pipeline

* hex-sampling: add STEP op

* hex-sampler: add SUM op

* hex-sampler: update CPY to support sampling cases

* hex-binary: add support for chunking to handle large logits

* hex-argmax: super basic version of ARGMAX

* hex-binary: support for scalars in extended buffers

* hex-binary: fix wrong indexing for dim 1 broadcasts across dim 2 slices

* hex-argsort: fix missing header

* hex-sampler: cleanup dma usage in the sampler related ops, and binary

* hex-build: disable autovectorizer, it is better to use explicit hints for critical loops

* hex-binary: fix perf regression due to is_1d fallback

* hex-ops: update supported ops
This commit is contained in:
Max Krasnyansky
2026-09-26 20:29:36 -07:00
committed by GitHub
parent 95887577ab
commit 2b129ccfa0
21 changed files with 12611 additions and 10816 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test-backend-ops.cpp
+1
View File
@@ -9830,6 +9830,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
add_test_bin_bcast(type, {5120, 1, 1, 1}, {1, 256, 1, 1});
add_test_bin_bcast(type, {640, 1, 1, 1}, {1, 1, 1, 1});
add_test_bin_bcast(type, {64, 262144, 1, 1}, {1, 1, 1, 1});
add_test_bin_bcast(type, {128, 1, 8, 1}, {1, 4, 1, 1});
//add_test_bin_bcast(type, {3, 3, 2560, 1280}, {1, 1, 1, 1});
//add_test_bin_bcast(type, {3, 3, 2560, 1280}, {2, 1, 1, 1});
}