mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-07-03 04:46:54 -04:00
Code Issues Packages Projects Releases Wiki Activity

feat(paged): add cublas route trace patch

Browse Source 
Add patch 0062 with default-off LLAMA_CUBLAS_ROUTE_TRACE instrumentation for generic cuBLAS MUL_MAT subroutes.

Record Phase 36 DGX gates, serving trace results, and the next projection follow-up scope.

Assisted-by: Codex:gpt-5
This commit is contained in:
Ettore Di Giacinto
2026-07-01 06:24:46 +00:00
parent 49cce0b5a2
commit fbdc200886
7 changed files with 508 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
backend/cpp/llama-cpp-localai-paged/docs/PATCH_MAINTENANCE.md
View File

@@ -57,18 +57,18 @@ everywhere without ever touching the stock `llama-cpp` source tree.
## Latest mirror check
Phase 35 re-verified the mirror invariant after adding patch `0061`:
Phase 36 re-verified the mirror invariant after adding patch `0062`:
```text
base=0ed235ea2c17a19fc8238668653946721ed136fd
applied_tree=305ebb96801822f2132ed9e9c868308b0759c7b9
fork_tree=305ebb96801822f2132ed9e9c868308b0759c7b9
applied_tree=208189d119efe27477f1900cc6f7428bd1720449
fork_tree=208189d119efe27477f1900cc6f7428bd1720449
```
The check used a fresh worktree at `LLAMA_VERSION`, applied every
`patches/paged/0*.patch` with strict `git apply`, staged the result, and compared
`git write-tree` to canonical fork branch `localai-paged` at
`486c28c63 feat(cuda): trace mul mat routes`.
`38c4ef2e4 feat(cuda): trace cublas routes`.
## Status