nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity

ggml : extend ggml_pool_1d + metal (#16429)

Browse Source 
* chore: resolve conflicts

* feat: ggml metal impl

* fix: ggml_metal_kargs_pool_1d struct

* fix: require contiguous input

* chore: test pool_1d

* chore: limit pool1d test cases to p0=0 and s0=k0 to conform with asserts

* chore: add p0 and s0 to testing

* fix: allow padding for cpu and metal

* Update ggml/src/ggml-metal/ggml-metal.metal

* fix: correct single-threaded loop

* ggml : cleanup

* tests : add ne[1] != 1 tests

* fix: ne[1] handling in np

* cont : fixes

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Thore Koritzius
2026-01-16 16:59:56 +02:00
committed by GitHub
co-authored by Georgi Gerganov
parent 6ba6a3c76f
commit 388ce82241
10 changed files with 272 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml.c
+5
View File
@@ -4838,6 +4838,8 @@ struct ggml_tensor * ggml_pool_1d(
a->ne[2],
a->ne[3],
};
GGML_ASSERT(ne[0] > 0);
struct ggml_tensor * result = ggml_new_tensor(ctx, GGML_TYPE_F32, 4, ne);
int32_t params[] = { op, k0, s0, p0 };
@@ -4868,6 +4870,9 @@ struct ggml_tensor * ggml_pool_2d(
a->ne[2],
a->ne[3],
};
GGML_ASSERT(ne[0] > 0);
GGML_ASSERT(ne[1] > 0);
result = ggml_new_tensor(ctx, GGML_TYPE_F32, 4, ne);
int32_t params[] = { op, k0, k1, s0, s1, p0, p1 };