Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.devops/musa.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/close-issue.yml
#	ci/README.md
#	docs/build.md
#	docs/docker.md
#	ggml/CMakeLists.txt
#	ggml/cmake/ggml-config.cmake.in
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/aclnn_ops.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cuda/fattn-wmma-f16.cu
#	ggml/src/ggml-musa/CMakeLists.txt
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
#	tools/imatrix/README.md
#	tools/imatrix/imatrix.cpp
This commit is contained in:
Concedo
2025-07-25 19:53:13 +08:00
33 changed files with 501 additions and 348 deletions
+19 -2
View File
@@ -651,6 +651,9 @@ void llama_model::load_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_RESIDUAL_SCALE, hparams.f_residual_scale);
ml.get_key(LLM_KV_LOGIT_SCALE, hparams.f_logit_scale);
// MiniCPM uses rope by default, unlike Granite which uses it as a switch
hparams.rope_finetuned = true;
switch (hparams.n_layer) {
case 52: type = LLM_TYPE_1B; break;
case 40: type = LLM_TYPE_2B; break;
@@ -1549,7 +1552,11 @@ void llama_model::load_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_TOKEN_SHIFT_COUNT, hparams.token_shift_count, false);
switch (hparams.n_layer) {
case 12: type = LLM_TYPE_190M; break;
case 12:
switch (hparams.n_embd) {
case 768: type = LLM_TYPE_190M; break;
default: type = LLM_TYPE_UNKNOWN;
} break;
case 24:
switch (hparams.n_embd) {
case 1024: type = LLM_TYPE_450M; break;
@@ -1562,7 +1569,17 @@ void llama_model::load_hparams(llama_model_loader & ml) {
case 3584: type = LLM_TYPE_7B; break;
default: type = LLM_TYPE_UNKNOWN;
} break;
case 32: type = LLM_TYPE_2_9B; break; // RWKV-7-World
case 32:
switch (hparams.n_embd) {
case 2560: type = LLM_TYPE_2_9B; break;
case 4096: type = LLM_TYPE_7B; break;
default: type = LLM_TYPE_UNKNOWN;
} break;
case 61:
switch (hparams.n_embd) {
case 4096: type = LLM_TYPE_14B; break;
default: type = LLM_TYPE_UNKNOWN;
} break;
default: type = LLM_TYPE_UNKNOWN;
}
} break;