fix(autogptq): do not use_triton with qwen-vl (mudler#1985)

* Enhance autogptq backend to support VL models

* update dependencies for autogptq

* remove redundant auto-gptq dependency

* Convert base64 to image_url for Qwen-VL model

* implemented model inference for qwen-vl

* remove user prompt from generated answer

* fixed write image error

* fixed use_triton issue when loading Qwen-VL model

---------

Co-authored-by: Binghua Wu <bingwu@estee.com>

ci: push latest images for dockerhub (mudler#1984)

Fixes: mudler#1983

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

ci: fixup latest image push

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

tests(petals): temp disable

⬆️ Update ggerganov/llama.cpp (mudler#1897)

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>

test/fix: OSX Test Repair (mudler#1843)

* test with gguf instead of ggml. Updates testPrompt to match? Adds debugging line to Dockerfile that I've found helpful recently.

* fix testPrompt slightly

* Sad Experiment: Test GH runner without metal?

* break apart CGO_LDFLAGS

* switch runner

* upstream llama.cpp disables Metal on Github CI!

* missed a dir from clean-tests

* CGO_LDFLAGS

* tmate failure + NO_ACCELERATE

* whisper.cpp has a metal fix

* do the exact opposite of the name of this branch, but keep it around for unrelated fixes?

* add back newlines

* add tmate to linux for testing

* update fixtures

* timeout for tmate

⬆️ Update ggerganov/llama.cpp (mudler#1840)

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>

⬆️ Update ggerganov/llama.cpp (mudler#1750)

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>

fix(tts): fix regression when supplying backend from requests (mudler…

…#1713)

fixes mudler#1707

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

fix(python): pin exllama2 (mudler#1711)

fix(python): pin python deps

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