]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 2d97363)
ggml : fix broken CPU concat implementation for quantized types (#25247)
authorfairydreaming <redacted>
Sat, 4 Jul 2026 11:37:37 +0000 (13:37 +0200)
committerGitHub <redacted>
Sat, 4 Jul 2026 11:37:37 +0000 (13:37 +0200)
commitef2d770117db45b05aa7ecd1b0acca36370c5470
tree86b4a755cfb9cad2799109ce453f02411357d7ectree
parent2d973636e292ee6f75fadcf08d29cb33511f509fcommit | diff
ggml : fix broken CPU concat implementation for quantized types (#25247)

* ggml : fix broken CPU concat implementation for quantized types

* tests : concat tests for quantized types

---------

Co-authored-by: Stanisław Szymczyk <redacted>
ggml/src/ggml-cpu/ops.cpp diff | blob | history
tests/test-backend-ops.cpp diff | blob | history
Packaging of ggml-org/llama.cpp