]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 47182dd)
llama : rename missed batch params/vars to ubatch (#10059)
authorDaniel Bevenius <redacted>
Mon, 6 Jan 2025 09:28:17 +0000 (10:28 +0100)
committerGitHub <redacted>
Mon, 6 Jan 2025 09:28:17 +0000 (11:28 +0200)
commit6369f867a410416239d9f20ec27c2b1d6a9fee52
treecbc8bef87b32d2d4397e64691344259234807599tree
parent47182dd03fe04a4ffda5d7f4c8a109ae0056cf56commit | diff
llama : rename missed batch params/vars to ubatch (#10059)

This commit renames the `batch` parameter to `ubatch` in the
`llama_kv_cache_find_slot`, `llm_build_inp_embd`, and
`llm_build_mamba` functions.

The motivation for this is that this should have been done as part of
Commit 19d900a7565b8f6b0a708836a57d26966cb9efe2 ("llama : rename batch
to ubatch (#9950)") but for some reason I missed these functions in
that commit and only noticed them now (sorry).
src/llama-kv-cache.cpp diff | blob | history
src/llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp