Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

metal : support argsort for ne00 > 1024 (#17247)

Browse Source 
* metal : refactor argsort

* cont : sort chunks

* cont : merge sorted buckets

* cont : cleanup
This commit is contained in:
Georgi Gerganov
2025-11-14 09:36:06 +02:00
committed by GitHub
parent 2606b0adab
commit 45c6ef7307
8 changed files with 266 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-metal/ggml-metal-device.h
+1
View File
@@ -125,6 +125,7 @@ ggml_metal_pipeline_t ggml_metal_library_get_pipeline_mul_mm_id (ggml_me
ggml_metal_pipeline_t ggml_metal_library_get_pipeline_mul_mv_id (ggml_metal_library_t lib, const struct ggml_tensor * op);
ggml_metal_pipeline_t ggml_metal_library_get_pipeline_argmax (ggml_metal_library_t lib, const struct ggml_tensor * op);
ggml_metal_pipeline_t ggml_metal_library_get_pipeline_argsort (ggml_metal_library_t lib, const struct ggml_tensor * op);
ggml_metal_pipeline_t ggml_metal_library_get_pipeline_argsort_merge (ggml_metal_library_t lib, const struct ggml_tensor * op);
ggml_metal_pipeline_t ggml_metal_library_get_pipeline_bin (ggml_metal_library_t lib, enum ggml_op op, int32_t n_fuse, bool row);
ggml_metal_pipeline_t ggml_metal_library_get_pipeline_l2_norm (ggml_metal_library_t lib, const struct ggml_tensor * op);
ggml_metal_pipeline_t ggml_metal_library_get_pipeline_group_norm (ggml_metal_library_t lib, const struct ggml_tensor * op);