koboldcpp/tools
Concedo 4fd0ceee30 Merge branch 'upstream' into concedo_experimental
# Conflicts:
#	common/chat.cpp
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cpy.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q4_0_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q4_k_f32.cl
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/dequantize.hpp
#	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
#	scripts/sync_vendor.py
#	tests/CMakeLists.txt
#	tests/peg-parser/tests.h
#	tests/test-backend-ops.cpp
#	tests/test-chat-auto-parser.cpp
#	tests/test-chat.cpp
#	tests/test-peg-parser.cpp
#	tools/llama-bench/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/server/README.md
2026-10-10 23:40:34 +08:00
..
batched-bench batch: migrate the rest of examples to llama_batch_ext (#29601) 2026-09-30 18:08:43 +02:00
cli Merge commit 'b42b7e6d30' into concedo_experimental 2026-10-10 13:37:53 +08:00
completion llama: support MoE cache over multiple GPUs (#30112) 2026-10-08 15:50:49 +05:30
fit-params server: use port 9931 by default (#30159) 2026-10-09 10:40:03 +02:00
gguf-split Merge branch 'upstream' into concedo_experimental 2026-08-14 18:10:18 +08:00
llama-bench llama-bench: respect -fitc if bigger than required benchmark size (#28331) 2026-10-09 19:14:30 +02:00
mtmd Merge commit '033df86b69' into concedo_experimental 2026-10-10 13:19:02 +08:00
perplexity batch: migrate the rest of examples to llama_batch_ext (#29601) 2026-09-30 18:08:43 +02:00
quantize Merge branch 'upstream' into concedo_experimental 2026-08-28 22:29:03 +08:00
rpc Merge branch 'upstream' into concedo_experimental 2026-10-03 17:59:14 +08:00
server Merge branch 'upstream' into concedo_experimental 2026-10-10 23:40:34 +08:00
tts Merge commit 'deae5ee133' into concedo_experimental 2026-08-28 19:31:29 +08:00
tuning Merge branch 'upstream' into concedo_experimental 2026-09-24 16:44:08 +08:00
ui unsync: maintaining lcpp ui is too much trouble. revert to upstream for now, but the compiled bundled lcpp will be frozen from before 2026-10-10 13:27:18 +08:00
kcpplauncherhook.py Switched VS2019 for revert cu12.1 build, hopefully solves dll issues 2025-06-10 23:08:02 +08:00