vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# 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
commit 0fcfbdb93c
33 changed files with 501 additions and 348 deletions
Download patch file Download diff file Expand all files Collapse all files

2
include/llama.h
View file

@ -959,6 +959,7 @@ extern "C" {
// in the order they have appeared in the batch.
// Rows: number of tokens for which llama_batch.logits[i] != 0
// Cols: n_vocab
// TODO: deprecate in favor of llama_get_logits_ith() (ref: https://github.com/ggml-org/llama.cpp/pull/14853#issuecomment-3113143522)
LLAMA_API float * llama_get_logits(struct llama_context * ctx);
// Logits for the ith token. For positive indices, Equivalent to:
@ -973,6 +974,7 @@ extern "C" {
// in the order they have appeared in the batch.
// shape: [n_outputs*n_embd]
// Otherwise, returns NULL.
// TODO: deprecate in favor of llama_get_embeddings_ith() (ref: https://github.com/ggml-org/llama.cpp/pull/14853#issuecomment-3113143522)
LLAMA_API float * llama_get_embeddings(struct llama_context * ctx);
// Get the embeddings for the ith token. For positive indices, Equivalent to: