From: LoganDark <redacted>
Date: Wed, 7 Jun 2023 16:16:19 +0000 (-0700)
Subject: ggml : correct off-by-one bounds check in ggml_compute_forward_set_f32 (#229)
X-Git-Tag: upstream/0.0.1642~1414
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=76cf2d647beedd26e6cf519bafec51e215b808a8;p=pkg%2Fggml%2Fsources%2Fggml

ggml : correct off-by-one bounds check in ggml_compute_forward_set_f32 (#229)

without this fix you will be unable to set a zero-length tensor to the end of another tensor

this sounds stupid, but is used in my testing
---

diff --git a/src/ggml.c b/src/ggml.c
index f4150161..c485733f 100644
--- a/src/ggml.c
+++ b/src/ggml.c
@@ -10359,7 +10359,7 @@ static void ggml_compute_forward_set_f32(
     const int im2 = (ne12 == 0 ? 0 : ne12-1);
     const int im3 = (ne13 == 0 ? 0 : ne13-1);
 
-    GGML_ASSERT(offset + im0*nb0  + im1*nb1  + im2*nb2  + im3*nb3  < ggml_nbytes(dst));
+    GGML_ASSERT(offset + im0*nb0  + im1*nb1  + im2*nb2  + im3*nb3  <= ggml_nbytes(dst));
 
     GGML_ASSERT(nb10 == sizeof(float));