chore(ci): fixup release pipeline

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

chore: ⬆️ Update ggml-org/llama.cpp to `be48528b068111304e4a0bb82c028…

…558b5705f05` (mudler#6012)

⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>

chore(build): Rename sycl to intel (mudler#5964)

Signed-off-by: Richard Palethorpe <io@richiejp.com>

chore: ⬆️ Update ggml-org/llama.cpp to `daf2dd788066b8b239cb7f68210e0…

…90c2124c199` (mudler#5951)

⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>

fix(backend gallery): intel images for python-based backends, re-add …

…exllama2 (mudler#5928)

chore(backend gallery): fix intel images for python-based backends

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

fix(cuda): be consistent with image tag naming (mudler#5916)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

fix(ci): add nvidia-l4t capability to l4t images (mudler#5914)

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>

fix(backends gallery): pass-by backend galleries to the model service (…

…mudler#5906)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

Update backends.md

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>

chore: ⬆️ Update ggml-org/llama.cpp to `72babea5dea56c8a8e8420ccf731b…

…12a5cf37854` (mudler#5743)

⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>