ci: fix thread sanitizer + remove ccache (ggml-org#26927)

* test address on Intel-LNL-U7-258V

* retry

* run address on github

* use native build for cpu

* this should be runnable everywhere multicore

* disable ccache

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

model : don't crash on unsupported architecture (ggml-org#22742)

* model: don't crash on unsupported architecture

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

Merge branch 'ggml-org:master' into master

ci: Merge ubuntu-cpu-riscv64-native into ubuntu-cpu job

Use ggml-org/ccache-action on RISC-V as well

vulkan: add FA dequant for q4_1, q5_0, q5_1, iq4_nl (ggml-org#21029)

Add dequantize4() implementations for Q4_1, Q5_0, Q5_1, and IQ4_NL
in the flash attention base shader. Register them in the shader
generator, pipeline creation, and enable in the scalar/coopmat1 FA
support check.

Relax prefill parser to allow space. (ggml-org#21240)

* Relax prefill parser to allow space.

* Move changes from prefix() to parser generation

* Only allow spaces if we're not having a pure content parser next

add missing ROPE_FACTORS_LONG/SHORT for MiniCPM (ggml-org#21150)

fix(ggml): correct RISC-V ISA string canonical ordering for RVV in CM…

…ake (ggml-org#20888)

Signed-off-by: ihb2032 <hebome@foxmail.com>

ggml-cpu/x86: fix unused changemask warning in repack (ggml-org#20692)