vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/full-rocm.Dockerfile
#	.devops/llama-cli-rocm.Dockerfile
#	.devops/llama-server-rocm.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/python-type-check.yml
#	CMakeLists.txt
#	CONTRIBUTING.md
#	README.md
#	ci/run.sh
#	examples/embedding/embedding.cpp
#	examples/server/README.md
#	flake.lock
#	ggml/include/ggml.h
#	ggml/src/ggml.c
#	requirements/requirements-convert_legacy_llama.txt
#	scripts/sync-ggml.last
#	src/llama-vocab.cpp
#	src/llama.cpp
#	tests/test-backend-ops.cpp
#	tests/test-grad0.cpp
#	tests/test-tokenizer-0.cpp
This commit is contained in:
Concedo 2024-10-02 01:00:57 +08:00
commit ce7f9c9a2c
39 changed files with 103400 additions and 102738 deletions
Download patch file Download diff file Expand all files Collapse all files

6
examples/llava/clip.cpp
View file

@ -2535,12 +2535,6 @@ bool clip_image_batch_encode(clip_ctx * ctx, const int n_threads, const clip_ima
ggml_backend_cpu_set_n_threads(ctx->backend, n_threads);
}
#ifdef GGML_USE_METAL
if (ggml_backend_is_metal(ctx->backend)) {
ggml_backend_metal_set_n_cb(ctx->backend, n_threads);
}
#endif
ggml_backend_graph_compute(ctx->backend, gf);
// the last node is the embedding tensor