llama.cpp/.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
..
ISSUE_TEMPLATE github: update issue templates [no ci] (#18410) 2025-12-28 10:50:56 +01:00
actions ci : remove libcurl in releases (#18775) 2026-01-12 21:43:02 +01:00
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 repo : update links to new url (#11886) 2025-02-15 16:40:57 +02:00