Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '4aced7a63156555911157d3002f9d3ddef4a1e55' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/cann.Dockerfile
#	.devops/cpu.Dockerfile
#	.devops/cuda.Dockerfile
#	.devops/intel.Dockerfile
#	.devops/musa.Dockerfile
#	.devops/rocm.Dockerfile
#	.devops/tools.sh
#	.devops/vulkan.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	.gitignore
#	docs/ops.md
#	docs/ops/SYCL.csv
#	examples/batched/batched.cpp
#	examples/eval-callback/eval-callback.cpp
#	examples/gen-docs/gen-docs.cpp
#	examples/lookahead/lookahead.cpp
#	examples/lookup/lookup-create.cpp
#	examples/lookup/lookup-stats.cpp
#	examples/lookup/lookup.cpp
#	examples/model-conversion/scripts/causal/compare-logits.py
#	examples/model-conversion/scripts/causal/run-org-model.py
#	examples/model-conversion/scripts/utils/check-nmse.py
#	examples/parallel/parallel.cpp
#	examples/retrieval/retrieval.cpp
#	examples/save-load-state/save-load-state.cpp
#	examples/speculative-simple/speculative-simple.cpp
#	examples/speculative/speculative.cpp
#	examples/training/finetune.cpp
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/repack.cpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/dequantize.hpp
#	ggml/src/ggml-sycl/dpct/helper.hpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/element_wise.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/pad.cpp
#	ggml/src/ggml-sycl/ssm_conv.cpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	pyrightconfig.json
#	scripts/sync-ggml.last
#	tests/test-arg-parser.cpp
#	tests/test-backend-ops.cpp
#	tools/cvector-generator/cvector-generator.cpp
#	tools/imatrix/imatrix.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/clip.cpp
#	tools/perplexity/perplexity.cpp
#	tools/server/README.md
This commit is contained in:
Concedo
2025-12-16 23:14:12 +08:00
parent e88bf41fdc 4aced7a631
commit 050a5b1f52
72 changed files with 4190 additions and 3086 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-kv-cache.cpp
+4 -9
View File
@@ -1369,9 +1369,10 @@ ggml_tensor * llama_kv_cache::build_rope_shift(
float freq_scale) const {
const auto & n_ctx_orig = cparams.n_ctx_orig_yarn;
const auto & yarn_ext_factor = cparams.yarn_ext_factor;
const auto & yarn_beta_fast = cparams.yarn_beta_fast;
const auto & yarn_beta_slow = cparams.yarn_beta_slow;
const auto & yarn_ext_factor = cparams.yarn_ext_factor;
const auto & yarn_beta_fast = cparams.yarn_beta_fast;
const auto & yarn_beta_slow = cparams.yarn_beta_slow;
const auto & yarn_attn_factor = cparams.yarn_attn_factor;
const auto & n_rot = hparams.n_rot;
const auto & rope_type = hparams.rope_type == LLAMA_ROPE_TYPE_MROPE || hparams.rope_type == LLAMA_ROPE_TYPE_IMROPE
@@ -1382,12 +1383,6 @@ ggml_tensor * llama_kv_cache::build_rope_shift(
? LLAMA_ROPE_TYPE_NEOX
: hparams.rope_type;
// See llm_build_deepseek2() for why attn_factor has to be scaled for YaRN RoPE to work correctly.
// See https://github.com/ggerganov/llama.cpp/discussions/7416 for detailed explanation.
const float yarn_attn_factor = model.arch == LLM_ARCH_DEEPSEEK2
? 1.0f / (1.0f + 0.1f * logf(1.0f / freq_scale))
: cparams.yarn_attn_factor;
ggml_tensor * tmp;
if (ggml_is_quantized(cur->type)) {