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/llama-cpp-cuda.srpm.spec
#	.devops/llama-cpp.srpm.spec
#	.devops/nix/package.nix
#	.devops/rocm.Dockerfile
#	.github/ISSUE_TEMPLATE/020-enhancement.yml
#	.github/ISSUE_TEMPLATE/030-research.yml
#	.github/ISSUE_TEMPLATE/040-refactor.yml
#	.github/ISSUE_TEMPLATE/config.yml
#	.github/pull_request_template.md
#	.github/workflows/bench.yml.disabled
#	.github/workflows/build.yml
#	.github/workflows/labeler.yml
#	CONTRIBUTING.md
#	Makefile
#	README.md
#	SECURITY.md
#	ci/README.md
#	common/CMakeLists.txt
#	docs/android.md
#	docs/backend/SYCL.md
#	docs/build.md
#	docs/cuda-fedora.md
#	docs/development/HOWTO-add-model.md
#	docs/docker.md
#	docs/install.md
#	docs/llguidance.md
#	examples/cvector-generator/README.md
#	examples/imatrix/README.md
#	examples/imatrix/imatrix.cpp
#	examples/llama.android/llama/src/main/cpp/CMakeLists.txt
#	examples/llama.swiftui/README.md
#	examples/llama.vim
#	examples/lookahead/README.md
#	examples/lookup/README.md
#	examples/main/README.md
#	examples/passkey/README.md
#	examples/pydantic_models_to_grammar_examples.py
#	examples/retrieval/README.md
#	examples/server/CMakeLists.txt
#	examples/server/README.md
#	examples/simple-cmake-pkg/README.md
#	examples/speculative/README.md
#	flake.nix
#	grammars/README.md
#	pyproject.toml
#	scripts/check-requirements.sh
This commit is contained in:
Concedo 2025-02-16 02:08:39 +08:00
commit f144b1f345
44 changed files with 276250 additions and 93 deletions
Download patch file Download diff file Expand all files Collapse all files

4
ggml/src/ggml-cpu/ggml-cpu.c
View file

@ -1821,7 +1821,7 @@ inline static float ggml_silu_f32(float x) {
#if __FINITE_MATH_ONLY__
#error "some routines in ggml.c require non-finite math arithmetics -- pass -fno-finite-math-only to the compiler to fix"
#error "ref: https://github.com/ggerganov/llama.cpp/pull/7154#issuecomment-2143844461"
#error "ref: https://github.com/ggml-org/llama.cpp/pull/7154#issuecomment-2143844461"
#endif
#if defined(__ARM_NEON) && defined(__aarch64__)
@ -7613,7 +7613,7 @@ UseGgmlGemm2:;
int64_t nchunk1 = (nr1 + chunk_size - 1) / chunk_size;
// If the chunking is poor for the number of threads on this setup, scrap the whole plan. Re-chunk it by thread.
// Also, chunking by thread was measured to have perform better on NUMA systems. See https://github.com/ggerganov/llama.cpp/pull/6915
// Also, chunking by thread was measured to have perform better on NUMA systems. See https://github.com/ggml-org/llama.cpp/pull/6915
// In theory, chunking should be just as useful on NUMA and non NUMA systems, but testing disagreed with that.
if (nchunk0 * nchunk1 < nth * 4 || ggml_is_numa()) {
// distribute the thread work across the inner or outer loop based on which one is larger