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 '5aba5364d959756c43eccc45596731e7b4eb3aa4' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build-apple.yml
#	.github/workflows/build-cpu.yml
#	.github/workflows/build-openvino.yml
#	.github/workflows/build-rpc.yml
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/build-vulkan.yml
#	.github/workflows/build-webgpu.yml
#	.github/workflows/server.yml
#	SECURITY.md
#	docs/backend/SYCL.md
#	docs/backend/ZenDNN.md
#	docs/build.md
#	docs/ops.md
#	docs/ops/SYCL.csv
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/dequantize.hpp
#	ggml/src/ggml-sycl/dmmv.cpp
#	ggml/src/ggml-sycl/fattn-common.hpp
#	ggml/src/ggml-sycl/getrows.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/quants.hpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	tests/test-reasoning-budget.cpp
#	tools/llama-bench/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/mtmd/CMakeLists.txt
This commit is contained in:
Concedo
2026-06-02 18:30:40 +08:00
parent 241ece07c3 5aba5364d9
commit 153214c66a
38 changed files with 834 additions and 258 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.cpp
-4
View File
@@ -3413,10 +3413,6 @@ llama_context * llama_init_from_model(
LLAMA_LOG_ERROR("%s: SPLIT_MODE_TENSOR requires flash_attn to be enabled\n", __func__);
return nullptr;
}
if (ggml_is_quantized(params.type_k) || ggml_is_quantized(params.type_v)) {
LLAMA_LOG_ERROR("%s: simultaneous use of SPLIT_MODE_TENSOR and KV cache quantization not implemented\n", __func__);
return nullptr;
}
}
if (params.flash_attn_type != LLAMA_FLASH_ATTN_TYPE_DISABLED && ggml_is_quantized(params.type_k)) {