vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'ggerganov:master' into fix-control-vector-loading

Browse source
This commit is contained in:
jukofyork 2024-06-27 07:27:36 +01:00 • committed by GitHub
commit 0395a3c4f2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 49 additions and 50 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/llama.android/llama/src/main/cpp/llama-android.cpp
View file

@ -5,7 +5,7 @@
#include <string>
#include <unistd.h>
#include "llama.h"
#include "common/common.h"
#include "common.h"
// Write C++ code here.
//

26
examples/llava/clip.cpp
View file

@ -1121,20 +1121,20 @@ struct clip_ctx * clip_model_load(const char * fname, const int verbosity = 1) {
}
if (n < 32)
hparams.image_grid_pinpoints[n] = 0;
} catch (std::runtime_error & e) {
} catch (std::runtime_error & /*e*/) {
hparams.image_grid_pinpoints[0]=0;
}
try {
int idx = get_key_idx(ctx, KEY_MM_PATCH_MERGE_TYPE);
strcpy(hparams.mm_patch_merge_type, gguf_get_val_str(ctx, idx));
} catch (std::runtime_error & e) {
} catch (std::runtime_error & /*e*/) {
strcpy(hparams.mm_patch_merge_type, "flat");
}
try {
hparams.image_crop_resolution = get_u32(ctx, KEY_IMAGE_CROP_RESOLUTION); // llava-1.6
} catch(const std::exception& e) {
} catch(const std::exception& /*e*/) {
hparams.image_crop_resolution = hparams.image_size;
}
@ -1173,7 +1173,7 @@ struct clip_ctx * clip_model_load(const char * fname, const int verbosity = 1) {
try {
vision_model.class_embedding = get_tensor(new_clip->ctx_data, TN_CLASS_EMBD);
new_clip->has_class_embedding = true;
} catch (const std::exception& e) {
} catch (const std::exception& /*e*/) {
new_clip->has_class_embedding = false;
}
@ -1181,7 +1181,7 @@ struct clip_ctx * clip_model_load(const char * fname, const int verbosity = 1) {
vision_model.pre_ln_w = get_tensor(new_clip->ctx_data, format(TN_LN_PRE, "v", "weight"));
vision_model.pre_ln_b = get_tensor(new_clip->ctx_data, format(TN_LN_PRE, "v", "bias"));
new_clip->has_pre_norm = true;
} catch (std::exception & e) {
} catch (std::exception & /*e*/) {
new_clip->has_pre_norm = false;
}
@ -1189,21 +1189,21 @@ struct clip_ctx * clip_model_load(const char * fname, const int verbosity = 1) {
vision_model.post_ln_w = get_tensor(new_clip->ctx_data, format(TN_LN_POST, "v", "weight"));
vision_model.post_ln_b = get_tensor(new_clip->ctx_data, format(TN_LN_POST, "v", "bias"));
new_clip->has_post_norm = true;
} catch (std::exception & e) {
} catch (std::exception & /*e*/) {
new_clip->has_post_norm = false;
}
try {
vision_model.patch_bias = get_tensor(new_clip->ctx_data, TN_PATCH_BIAS);
new_clip->has_patch_bias = true;
} catch (std::exception & e) {
} catch (std::exception & /*e*/) {
new_clip->has_patch_bias = false;
}
try {
vision_model.patch_embeddings = get_tensor(new_clip->ctx_data, TN_PATCH_EMBD);
vision_model.position_embeddings = get_tensor(new_clip->ctx_data, format(TN_POS_EMBD, "v"));
} catch(const std::exception& e) {
} catch(const std::exception& /*e*/) {
LOG_TEE("%s: failed to load vision model tensors\n", __func__);
}
@ -1215,26 +1215,26 @@ struct clip_ctx * clip_model_load(const char * fname, const int verbosity = 1) {
// Yi-type llava
vision_model.mm_1_w = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 1, "weight"));
vision_model.mm_1_b = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 1, "bias"));
} catch (std::runtime_error & e) { }
} catch (std::runtime_error & /*e*/) { }
try {
// missing in Yi-type llava
vision_model.mm_2_w = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 2, "weight"));
vision_model.mm_2_b = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 2, "bias"));
} catch (std::runtime_error & e) { }
} catch (std::runtime_error & /*e*/) { }
try {
// Yi-type llava
vision_model.mm_3_w = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 3, "weight"));
vision_model.mm_3_b = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 3, "bias"));
} catch (std::runtime_error & e) { }
} catch (std::runtime_error & /*e*/) { }
try {
// Yi-type llava
vision_model.mm_4_w = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 4, "weight"));
vision_model.mm_4_b = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 4, "bias"));
} catch (std::runtime_error & e) { }
} catch (std::runtime_error & /*e*/) { }
try {
vision_model.image_newline = get_tensor(new_clip->ctx_data, TN_IMAGE_NEWLINE);
// LOG_TEE("%s: image_newline tensor (llava-1.6) found\n", __func__);
} catch (std::runtime_error & e) { }
} catch (std::runtime_error & /*e*/) { }
} else if (new_clip->proj_type == PROJECTOR_TYPE_LDP) {
// MobileVLM projection
vision_model.mm_model_mlp_1_w = get_tensor(new_clip->ctx_data, format(TN_MVLM_PROJ_MLP, 1, "weight"));

71
scripts/sync-ggml-am.sh
View file

@ -136,42 +136,41 @@ if [ -f $SRC_LLAMA/ggml-src.patch ]; then
# LICENSE -> LICENSE
# scripts/gen-authors.sh -> scripts/gen-authors.sh
cat ggml-src.patch | sed \
-e 's/CMakeLists.txt/ggml\/CMakeLists.txt/g' \
-e 's/src\/CMakeLists.txt/ggml\/src\/CMakeLists.txt/g' \
-e 's/cmake\/FindSIMD.cmake/ggml\/cmake\/FindSIMD.cmake/g' \
-e 's/src\/ggml\.c/ggml/src/ggml.c/g' \
-e 's/src\/ggml-alloc\.c/ggml/src/ggml-alloc.c/g' \
-e 's/src\/ggml-backend-impl\.h/ggml/src/ggml-backend-impl.h/g' \
-e 's/src\/ggml-backend\.c/ggml/src/ggml-backend.c/g' \
-e 's/src\/ggml-common\.h/ggml/src/ggml-common.h/g' \
-e 's/src\/ggml-cuda\//ggml-cuda\//g' \
-e 's/src\/ggml-cuda\.cu/ggml/src/ggml-cuda.cu/g' \
-e 's/src\/ggml-impl\.h/ggml/src/ggml-impl.h/g' \
-e 's/src\/ggml-kompute\.cpp/ggml/src/ggml-kompute.cpp/g' \
-e 's/src\/ggml-metal\.m/ggml/src/ggml-metal.m/g' \
-e 's/src\/ggml-quants\.c/ggml/src/ggml-quants.c/g' \
-e 's/src\/ggml-quants\.h/ggml/src/ggml-quants.h/g' \
-e 's/src\/ggml-rpc\.cpp/ggml/src/ggml-rpc.cpp/g' \
-e 's/src\/ggml-sycl\.cpp/ggml/src/ggml-sycl.cpp/g' \
-e 's/src\/ggml-vulkan\.cpp/ggml/src/ggml-vulkan.cpp/g' \
-e 's/include\/ggml\.h/ggml/include/ggml.h/g' \
-e 's/include\/ggml-alloc\.h/ggml/include/ggml-alloc.h/g' \
-e 's/include\/ggml-backend\.h/ggml/include/ggml-backend.h/g' \
-e 's/include\/ggml-blas\.h/ggml/include/ggml-blas.h/g' \
-e 's/include\/ggml-cuda\.h/ggml/include/ggml-cuda.h/g' \
-e 's/include\/ggml-kompute\.h/ggml/include/ggml-kompute.h/g' \
-e 's/include\/ggml-metal\.h/ggml/include/ggml-metal.h/g' \
-e 's/include\/ggml-rpc\.h/ggml/include/ggml-rpc.h/g' \
-e 's/include\/ggml-sycl\.h/ggml/include/ggml-sycl.h/g' \
-e 's/include\/ggml-vulkan\.h/ggml/include/ggml-vulkan.h/g' \
-e 's/tests\/test-opt\.cpp/tests\/test-opt.cpp/g' \
-e 's/tests\/test-grad0\.cpp/tests\/test-grad0.cpp/g' \
-e 's/tests\/test-quantize-fns\.cpp/tests\/test-quantize-fns.cpp/g' \
-e 's/tests\/test-quantize-perf\.cpp/tests\/test-quantize-perf.cpp/g' \
-e 's/tests\/test-backend-ops\.cpp/tests\/test-backend-ops.cpp/g' \
-e 's/LICENSE/LICENSE/g' \
-e 's/scripts\/gen-authors\.sh/scripts\/gen-authors.sh/g' \
cat ggml-src.patch | sed -E \
-e 's/([[:space:]]|[ab]\/)CMakeLists.txt/\1ggml\/CMakeLists.txt/g' \
-e 's/([[:space:]]|[ab]\/)src\/CMakeLists.txt/\1ggml\/src\/CMakeLists.txt/g' \
-e 's/([[:space:]]|[ab]\/)cmake\/FindSIMD.cmake/\1ggml\/cmake\/FindSIMD.cmake/g' \
-e 's/([[:space:]]|[ab]\/)src\/ggml\.c/\1ggml\/src\/ggml.c/g' \
-e 's/([[:space:]]|[ab]\/)src\/ggml-alloc\.c/\1ggml\/src\/ggml-alloc.c/g' \
-e 's/([[:space:]]|[ab]\/)src\/ggml-backend-impl\.h/\1ggml\/src\/ggml-backend-impl.h/g' \
-e 's/([[:space:]]|[ab]\/)src\/ggml-backend\.c/\1ggml\/src\/ggml-backend.c/g' \
-e 's/([[:space:]]|[ab]\/)src\/ggml-common\.h/\1ggml\/src\/ggml-common.h/g' \
-e 's/([[:space:]]|[ab]\/)src\/ggml-cuda\//\1ggml\/src\/ggml-cuda\//g' \
-e 's/([[:space:]]|[ab]\/)src\/ggml-cuda\.cu/\1ggml\/src\/ggml-cuda.cu/g' \
-e 's/([[:space:]]|[ab]\/)src\/ggml-impl\.h/\1ggml\/src\/ggml-impl.h/g' \
-e 's/([[:space:]]|[ab]\/)src\/ggml-kompute\.cpp/\1ggml\/src\/ggml-kompute.cpp/g' \
-e 's/([[:space:]]|[ab]\/)src\/ggml-metal\.m/\1ggml\/src\/ggml-metal.m/g' \
-e 's/([[:space:]]|[ab]\/)src\/ggml-quants\.c/\1ggml\/src\/ggml-quants.c/g' \
-e 's/([[:space:]]|[ab]\/)src\/ggml-quants\.h/\1ggml\/src\/ggml-quants.h/g' \
-e 's/([[:space:]]|[ab]\/)src\/ggml-rpc\.cpp/\1ggml\/src\/ggml-rpc.cpp/g' \
-e 's/([[:space:]]|[ab]\/)src\/ggml-sycl\.cpp/\1ggml\/src\/ggml-sycl.cpp/g' \
-e 's/([[:space:]]|[ab]\/)src\/ggml-vulkan\.cpp/\1ggml\/src\/ggml-vulkan.cpp/g' \
-e 's/([[:space:]]|[ab]\/)include\/ggml\.h/\1ggml\/include\/ggml.h/g' \
-e 's/([[:space:]]|[ab]\/)include\/ggml-alloc\.h/\1ggml\/include\/ggml-alloc.h/g' \
-e 's/([[:space:]]|[ab]\/)include\/ggml-backend\.h/\1ggml\/include\/ggml-backend.h/g' \
-e 's/([[:space:]]|[ab]\/)include\/ggml-blas\.h/\1ggml\/include\/ggml-blas.h/g' \
-e 's/([[:space:]]|[ab]\/)include\/ggml-cuda\.h/\1ggml\/include\/ggml-cuda.h/g' \
-e 's/([[:space:]]|[ab]\/)include\/ggml-kompute\.h/\1ggml\/include\/ggml-kompute.h/g' \
-e 's/([[:space:]]|[ab]\/)include\/ggml-metal\.h/\1ggml\/include\/ggml-metal.h/g' \
-e 's/([[:space:]]|[ab]\/)include\/ggml-rpc\.h/\1ggml\/include\/ggml-rpc.h/g' \
-e 's/([[:space:]]|[ab]\/)include\/ggml-sycl\.h/\1ggml\/include\/ggml-sycl.h/g' \
-e 's/([[:space:]]|[ab]\/)include\/ggml-vulkan\.h/\1ggml\/include\/ggml-vulkan.h/g' \
-e 's/([[:space:]]|[ab]\/)examples\/common\.h/examples\/common.h/g' \
-e 's/([[:space:]]|[ab]\/)examples\/common\.cpp/examples\/common.cpp/g' \
-e 's/([[:space:]]|[ab]\/)examples\/common-ggml\.h/examples\/common-ggml.h/g' \
-e 's/([[:space:]]|[ab]\/)examples\/common-ggml\.cpp/examples\/common-ggml.cpp/g' \
-e 's/([[:space:]]|[ab]\/)LICENSE/LICENSE/g' \
-e 's/([[:space:]]|[ab]\/)scripts\/gen-authors\.sh/scripts\/gen-authors.sh/g' \
> ggml-src.patch.tmp
mv ggml-src.patch.tmp ggml-src.patch