upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-03 16:40:45 -05:00
Code Issues Packages Projects Releases Wiki Activity

nits

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-07-23 18:51:19 +02:00
parent b1f66cb3b8
commit b60794b60f
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
skills/code-review/SKILL.md
View File

@@ -90,8 +90,8 @@ See the `add-new-model` skill and `docs/development/HOWTO-add-model.md` for the
- New op or operator change needs corresponding `test-backend-ops` cases, and (per `CONTRIBUTING.md`) consistency across at least two backends.
- New kernels are expected to come with concrete perf data (throughput across realistic tensor shapes), not just correctness.
- Don't have a backend mutate the cgraph as a shortcut - that's an unresolved architectural question, not something to slip in.
- Expect this to need two maintainer approvals; that's normal for `ggml/` changes, not a sign something is wrong.
- For CUDA: Avoid excessively templating kernels, only add this where it shows visible performance gain.
- Expect this to need two maintainer approvals; that's normal for `ggml/` changes, not a sign something is wrong.
- For CUDA: Avoid excessively templating kernels, only add this where it shows visible performance gain.
## Public API (`include/llama.h`)