Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-13 10:18:49 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/cann.Dockerfile
#	.devops/cpu.Dockerfile
#	.devops/cuda.Dockerfile
#	.devops/intel.Dockerfile
#	.devops/llama-cli-cann.Dockerfile
#	.devops/musa.Dockerfile
#	.devops/openvino.Dockerfile
#	.devops/rocm.Dockerfile
#	.devops/s390x.Dockerfile
#	.devops/vulkan.Dockerfile
#	.github/ISSUE_TEMPLATE/011-bug-results.yml
#	.github/ISSUE_TEMPLATE/019-bug-misc.yml
#	.github/workflows/build-and-test-snapdragon.yml
#	.github/workflows/docker.yml
#	.github/workflows/server-self-hosted.yml
#	.github/workflows/ui-ci.yml
#	.pi/gg/SYSTEM.md
#	README.md
#	common/arg.cpp
#	docs/backend/SYCL.md
#	docs/backend/snapdragon/CMakeUserPresets.json
#	docs/backend/snapdragon/README.md
#	docs/speculative.md
#	examples/save-load-state/save-load-state.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/rope-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/gated_delta_net.wgsl
#	tools/cli/README.md
#	tools/server/README.md
This commit is contained in:
Concedo
2026-05-20 18:48:34 +08:00
parent 643862ac7d 585080d310
commit 7d987af23a
77 changed files with 1291 additions and 1048 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-memory-recurrent.cpp
+9 -3
View File
@@ -416,9 +416,15 @@ llama_memory_context_ptr llama_memory_recurrent::init_batch(llama_batch_allocr &
// if all tokens are output, split by sequence
ubatch = balloc.split_seq(n_ubatch);
} else {
// TODO: non-sequential equal split can be done if using unified KV cache
// for simplicity, we always use sequential equal split for now
ubatch = balloc.split_equal(n_ubatch, true);
if (n_rs_seq > 0) {
// [TAG_RECURRENT_ROLLBACK_SPLITS]
// TODO: recurrent state rollback does not support equal splits
ubatch = balloc.split_seq(n_ubatch);
} else {
// TODO: non-sequential equal split can be done if using unified KV cache
// for simplicity, we always use sequential equal split for now
ubatch = balloc.split_equal(n_ubatch, true);
}
}
if (ubatch.n_tokens == 0) {