Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +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
tools/server/server-context.cpp
+18 -11
View File
@@ -467,20 +467,26 @@ struct server_slot {
const double n_gen_second = 1e3 / t_token_generation * n_decoded;
SLT_INF(*this,
"\n"
"prompt eval time = %10.2f ms / %5d tokens (%8.2f ms per token, %8.2f tokens per second)\n"
" eval time = %10.2f ms / %5d tokens (%8.2f ms per token, %8.2f tokens per second)\n"
"prompt eval time = %10.2f ms / %5d tokens (%8.2f ms per token, %8.2f tokens per second)\n",
t_prompt_processing, n_prompt_tokens_processed, t_prompt, n_prompt_second);
SLT_INF(*this,
" eval time = %10.2f ms / %5d tokens (%8.2f ms per token, %8.2f tokens per second)\n",
t_token_generation, n_decoded, t_gen, n_gen_second);
SLT_INF(*this,
" total time = %10.2f ms / %5d tokens\n",
t_prompt_processing, n_prompt_tokens_processed, t_prompt, n_prompt_second,
t_token_generation, n_decoded, t_gen, n_gen_second,
t_prompt_processing + t_token_generation, n_prompt_tokens_processed + n_decoded);
SLT_INF(*this,
" graphs reused = %10d\n",
llama_perf_context(ctx_tgt).n_reused);
if (n_draft_total > 0) {
const float draft_ratio = (float) n_draft_accepted / n_draft_total;
SLT_CNT(*this,
"draft acceptance rate = %0.5f (%5d accepted / %5d generated)\n",
draft_ratio, n_draft_accepted, n_draft_total
);
SLT_INF(*this,
"draft acceptance = %0.5f (%5d accepted / %5d generated)\n",
draft_ratio, n_draft_accepted, n_draft_total);
}
common_speculative_print_stats(spec);
@@ -2583,9 +2589,9 @@ private:
llama_pos pos_next = slot.prompt.tokens.pos_next(n_past);
// the largest pos_min required for a checkpoint to be useful
const auto pos_min_thold = std::max(0, pos_next - n_swa);
const auto pos_min_thold = std::max(0, pos_next - n_swa - 1);
if (n_past > 0 && n_past < slot.prompt.n_tokens()) {
if (n_past > 0 && n_past <= slot.prompt.n_tokens()) {
const auto pos_min = llama_memory_seq_pos_min(llama_get_memory(ctx_tgt), slot.id);
if (pos_min == -1) {
SLT_ERR(slot, "n_past = %d, slot.prompt.tokens.size() = %d, seq_id = %d, pos_min = %d\n", n_past, (int) slot.prompt.tokens.size(), slot.id, pos_min);
@@ -3885,6 +3891,7 @@ void server_routes::init_routes() {
{ "eos_token", meta->eos_token_str },
{ "build_info", meta->build_info },
{ "is_sleeping", queue_tasks.is_sleeping() },
{ "cors_proxy_enabled", params.ui_mcp_proxy || params.webui_mcp_proxy },
};
if (params.use_jinja) {
if (!tmpl_tools.empty()) {
tools/server/server-models.cpp
+1
View File
@@ -1165,6 +1165,7 @@ void server_models_routes::init_routes() {
// Deprecated: use ui_settings instead (kept for backward compat)
{"webui_settings", webui_settings},
{"build_info", std::string(llama_build_info())},
{"cors_proxy_enabled", params.ui_mcp_proxy || params.webui_mcp_proxy},
});
return res;
}