Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-07 05:21:23 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '8f8f2274ee3601fecf6e2d57b52f701c81bede21' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/rocm.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	CMakeLists.txt
#	examples/simple/simple.cpp
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-opencl/kernels/tsembd.cl
#	ggml/src/ggml-sycl/binbcast.cpp
#	ggml/src/ggml-sycl/binbcast.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/tsembd.cpp
#	ggml/src/ggml-zdnn/ggml-zdnn.cpp
#	src/llama-model.cpp
#	tools/batched-bench/CMakeLists.txt
#	tools/cvector-generator/CMakeLists.txt
#	tools/export-lora/CMakeLists.txt
#	tools/gguf-split/CMakeLists.txt
#	tools/imatrix/CMakeLists.txt
#	tools/llama-bench/CMakeLists.txt
#	tools/llama-bench/llama-bench.cpp
#	tools/main/CMakeLists.txt
#	tools/main/README.md
#	tools/mtmd/CMakeLists.txt
#	tools/perplexity/CMakeLists.txt
#	tools/perplexity/perplexity.cpp
#	tools/quantize/CMakeLists.txt
#	tools/rpc/rpc-server.cpp
#	tools/run/CMakeLists.txt
#	tools/run/run.cpp
#	tools/tokenize/CMakeLists.txt
#	tools/tts/CMakeLists.txt
This commit is contained in:
Concedo
2025-09-21 08:58:23 +08:00
parent 04498a345a 8f8f2274ee
commit 3e72aaff5b
41 changed files with 1998 additions and 1463 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.cpp
+7 -7
View File
@@ -35,10 +35,10 @@ llama_context::llama_context(
cparams.n_threads = params.n_threads;
cparams.n_threads_batch = params.n_threads_batch;
cparams.yarn_ext_factor = params.yarn_ext_factor;
cparams.yarn_attn_factor = params.yarn_attn_factor;
cparams.yarn_beta_fast = params.yarn_beta_fast;
cparams.yarn_beta_slow = params.yarn_beta_slow;
cparams.yarn_ext_factor = params.yarn_ext_factor >= 0.0f ? params.yarn_ext_factor : hparams.yarn_ext_factor;
cparams.yarn_attn_factor = params.yarn_attn_factor >= 0.0f ? params.yarn_attn_factor : hparams.yarn_attn_factor;
cparams.yarn_beta_fast = params.yarn_beta_fast >= 0.0f ? params.yarn_beta_fast : hparams.yarn_beta_fast;
cparams.yarn_beta_slow = params.yarn_beta_slow >= 0.0f ? params.yarn_beta_slow : hparams.yarn_beta_slow;
cparams.embeddings = params.embeddings;
cparams.offload_kqv = params.offload_kqv;
cparams.no_perf = params.no_perf;
@@ -2263,9 +2263,9 @@ llama_context_params llama_context_default_params() {
/*.rope_freq_base =*/ 0.0f,
/*.rope_freq_scale =*/ 0.0f,
/*.yarn_ext_factor =*/ -1.0f,
/*.yarn_attn_factor =*/ 1.0f,
/*.yarn_beta_fast =*/ 32.0f,
/*.yarn_beta_slow =*/ 1.0f,
/*.yarn_attn_factor =*/ -1.0f,
/*.yarn_beta_fast =*/ -1.0f,
/*.yarn_beta_slow =*/ -1.0f,
/*.yarn_orig_ctx =*/ 0,
/*.defrag_thold =*/ -1.0f,
/*.cb_eval =*/ nullptr,