Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-03 11:35:48 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	CMakeLists.txt
#	docs/speculative.md
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-ops.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/rope-ops.c
#	ggml/src/ggml-hexagon/htp/ssm-conv.c
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	scripts/snapdragon/adb/run-bench.sh
#	scripts/snapdragon/adb/run-cli.sh
#	scripts/snapdragon/adb/run-completion.sh
#	scripts/snapdragon/adb/run-mtmd.sh
#	scripts/snapdragon/windows/run-bench.ps1
#	scripts/snapdragon/windows/run-cli.ps1
#	scripts/snapdragon/windows/run-completion.ps1
#	scripts/snapdragon/windows/run-mtmd.ps1
#	src/llama-vocab.cpp
#	tests/test-backend-ops.cpp
#	tools/batched-bench/CMakeLists.txt
#	tools/batched-bench/batched-bench.cpp
#	tools/cli/CMakeLists.txt
#	tools/cli/README.md
#	tools/cli/cli.cpp
#	tools/completion/CMakeLists.txt
#	tools/completion/README.md
#	tools/llama-bench/CMakeLists.txt
#	tools/llama-bench/llama-bench.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/tests/test-deepseek-ocr.py
#	tools/mtmd/tests/tests-requirements.txt
#	tools/perplexity/CMakeLists.txt
#	tools/perplexity/perplexity.cpp
#	tools/quantize/CMakeLists.txt
#	tools/server/CMakeLists.txt
#	tools/server/README.md
#	ty.toml
This commit is contained in:
Concedo
2026-05-21 23:47:21 +08:00
parent 54af9aada9 1d7ab2b947
commit 718dc159b6
83 changed files with 1469 additions and 648 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.cpp
+13
View File
@@ -1147,6 +1147,19 @@ bool llama_context::set_sampler(llama_seq_id seq_id, llama_sampler * sampler) {
LLAMA_LOG_DEBUG("%s: seq_id = %d, sampler = %p\n", __func__, (int) seq_id, (void *) sampler);
if (sampler && model.split_mode() == LLAMA_SPLIT_MODE_TENSOR) {
static bool warned = false;
if (!warned) {
LLAMA_LOG_WARN("%s: backend sampling not supported with SPLIT_MODE_TENSOR; using CPU\n", __func__);
warned = true;
}
if (sampling.samplers.count(seq_id) > 0) {
sched_need_reserve = true;
}
sampling.samplers.erase(seq_id);
return false;
}
const bool can_offload =
sampler &&
sampler->iface->backend_init &&