Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-08-25 22:21:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/nix/package.nix
#	.github/workflows/server.yml
#	docs/development/HOWTO-add-model.md
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/argsort-ops.c
#	ggml/src/ggml-hexagon/htp/concat-ops.c
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/gated-delta-net-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-ops.h
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/hvx-utils.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/pad-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-webgpu/wgsl-shaders/cpy.wgsl
#	scripts/sync_vendor.py
#	src/llama-context.cpp
#	tests/test-backend-sampler.cpp
#	tools/server/README.md
#	tools/ui/tests/stories/ChatScreenForm.a11y.stories.svelte
This commit is contained in:
Concedo
2026-06-02 19:28:39 +08:00
parent 153214c66a d5ab0834ab
commit 13eaa04269
78 changed files with 1801 additions and 477 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.cpp
+1 -3
View File
@@ -1395,8 +1395,6 @@ common_init_result_ptr common_init_from_params(common_params & params, bool mode
if (params.warmup) {
LOG_INF("%s: warming up the model with an empty run - please wait ... (--no-warmup to disable)\n", __func__);
llama_set_warmup(lctx, true);
std::vector<llama_token> tmp;
llama_token bos = llama_vocab_bos(vocab);
llama_token eos = llama_vocab_eos(vocab);
@@ -1427,7 +1425,6 @@ common_init_result_ptr common_init_from_params(common_params & params, bool mode
llama_memory_clear(llama_get_memory(lctx), true);
llama_synchronize(lctx);
llama_perf_context_reset(lctx);
llama_set_warmup(lctx, false);
// reset samplers to reset RNG state after warmup to the seeded state
res->reset_samplers();
@@ -1569,6 +1566,7 @@ struct llama_context_params common_context_params_to_llama(const common_params &
cparams.n_ctx = params.n_ctx;
cparams.n_seq_max = params.n_parallel;
cparams.n_rs_seq = params.speculative.need_n_rs_seq();
cparams.n_outputs_max = std::max(params.n_outputs_max, 0);
cparams.n_batch = params.n_batch;
cparams.n_ubatch = params.n_ubatch;
cparams.n_threads = params.cpuparams.n_threads;