llama_cpp_for_radxa_dragon_.../.github
Georgi Gerganov 557515be1e
graph : utilize ggml_build_forward_select() to avoid reallocations (#18898)
* graph : avoid branches between embedding and token inputs

* models : make deepstack graphs (e.g. Qwen3 VL) have constant topology

* ci : enable -DGGML_SCHED_NO_REALLOC=ON for server CI

* cont : pad token embeddings to n_embd_inp
2026-01-23 18:22:34 +02:00
..
actions
ISSUE_TEMPLATE
workflows graph : utilize ggml_build_forward_select() to avoid reallocations (#18898) 2026-01-23 18:22:34 +02:00
labeler.yml ci : add label for jinja changes (#18903) 2026-01-17 21:52:02 +01:00
pull_request_template.md