vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	README.md
#	ci/run.sh
#	docs/build.md
#	examples/CMakeLists.txt
#	examples/parallel/parallel.cpp
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	scripts/server-bench.py
#	src/llama-kv-cache-unified.cpp
#	tests/test-backend-ops.cpp
#	tools/batched-bench/batched-bench.cpp
#	tools/server/README.md
This commit is contained in:
Concedo 2025-07-17 00:28:37 +08:00
commit bdff33e0de
47 changed files with 3128 additions and 509 deletions
Download patch file Download diff file Expand all files Collapse all files

6
include/llama.h
View file

@ -338,6 +338,9 @@ extern "C" {
bool swa_full; // use full-size SWA cache (https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055)
// NOTE: setting to false when n_seq_max > 1 can cause bad performance in some cases
// ref: https://github.com/ggml-org/llama.cpp/pull/13845#issuecomment-2924800573
bool kv_unified; // use a unified buffer across the input sequences when computing the attention
// try to disable when n_seq_max > 1 for improved performance when the sequences do not share a large prefix
// ref: https://github.com/ggml-org/llama.cpp/pull/14363
};
// model quantization parameters
@ -728,7 +731,7 @@ extern "C" {
// - lazily on next llama_decode()
// p0 < 0 : [0, p1]
// p1 < 0 : [p0, inf)
DEPRECATED(void llama_kv_self_seq_div(
DEPRECATED(LLAMA_API void llama_kv_self_seq_div(
struct llama_context * ctx,
llama_seq_id seq_id,
llama_pos p0,
@ -1008,6 +1011,7 @@ extern "C" {
LLAMA_API llama_token llama_vocab_sep(const struct llama_vocab * vocab); // sentence separator
LLAMA_API llama_token llama_vocab_nl (const struct llama_vocab * vocab); // next-line
LLAMA_API llama_token llama_vocab_pad(const struct llama_vocab * vocab); // padding
LLAMA_API llama_token llama_vocab_mask(const struct llama_vocab * vocab); // mask
LLAMA_API bool llama_vocab_get_add_bos(const struct llama_vocab * vocab);
LLAMA_API bool llama_vocab_get_add_eos(const struct llama_vocab * vocab);