Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/workflows/build-apple.yml
#	.github/workflows/build-cpu.yml
#	.github/workflows/build-cuda-ubuntu.yml
#	.github/workflows/build-sycl.yml
#	.github/workflows/build-vulkan.yml
#	.github/workflows/build-wasm.yml
#	.github/workflows/build-webgpu.yml
#	.github/workflows/hip-quality-check.yml
#	.github/workflows/server.yml
#	CMakeLists.txt
#	docs/backend/SYCL.md
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/concat.cl
#	ggml/src/ggml-opencl/kernels/cpy.cl
#	ggml/src/ggml-sycl/common.cpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/fattn-buffers.cpp
#	ggml/src/ggml-sycl/fwht.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
#	tests/test-llama-archs.cpp
This commit is contained in:
Concedo
2026-09-05 12:09:30 +08:00
35 changed files with 1665 additions and 50 deletions
+1 -2
View File
@@ -1718,8 +1718,7 @@ struct clip_model_loader {
hparams.patch_size = hparams.patch_size * hparams.n_merge;
hparams.n_merge = 1;
}
// @ngxson : the model performs quite poor with small images, we need to bump minimum image tokens to 40 to avoid that
hparams.set_limit_image_tokens(40, 280);
hparams.set_limit_image_tokens(70, 1120);
hparams.set_warmup_n_tokens(256); // avoid OOM on warmup
} break;