llama: update vendored code to commit 40c6d79f (#7875)

527cc978 · Jeffrey Morgan · GitHub · a37f4a86 · 527cc978 · 527cc978
Unverified Commit 527cc978 authored Dec 10, 2024 by Jeffrey Morgan Committed by GitHub Dec 10, 2024
20 changed files
--- a/llama/ggml-cuda/sum.cu
+++ b/llama/ggml-cuda/sum.cu
--- a/llama/ggml-cuda/sum.cuh
+++ b/llama/ggml-cuda/sum.cuh
--- a/llama/ggml-cuda/sumrows.cu
+++ b/llama/ggml-cuda/sumrows.cu
--- a/llama/ggml-cuda/sumrows.cuh
+++ b/llama/ggml-cuda/sumrows.cuh
--- a/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-f16.cu
+++ b/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-f16.cu
--- a/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_0.cu
+++ b/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_0.cu
--- a/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_1.cu
+++ b/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_1.cu
--- a/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_0.cu
+++ b/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_0.cu
--- a/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_1.cu
+++ b/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_1.cu
--- a/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q8_0.cu
+++ b/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q8_0.cu
--- a/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-f16.cu
+++ b/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-f16.cu
--- a/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_0.cu
+++ b/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_0.cu
--- a/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_1.cu
+++ b/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_1.cu
--- a/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_0.cu
+++ b/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_0.cu
--- a/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_1.cu
+++ b/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_1.cu
--- a/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q8_0.cu
+++ b/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q8_0.cu
--- a/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-f16.cu
+++ b/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-f16.cu
--- a/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_0.cu
+++ b/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_0.cu
--- a/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_1.cu
+++ b/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_1.cu
--- a/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_0.cu
+++ b/llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_0.cu