mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-09-18 16:55:14 +02:00
Merge commit 'f534da26e4ab045b6899adc07cd2b9a065355ce9' into concedo_experimental
# Conflicts: # .github/workflows/release.yml # docs/ops.md # docs/ops/WebGPU.csv # ggml/src/CMakeLists.txt # ggml/src/ggml-cpu/kleidiai/kleidiai.cpp # ggml/src/ggml-hexagon/ggml-hexagon.cpp # ggml/src/ggml-openvino/ggml-openvino.cpp # ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp # ggml/src/ggml-webgpu/ggml-webgpu.cpp # models/templates/deepseek-ai-DeepSeek-V4.jinja # tests/test-backend-ops.cpp # tests/test-chat-auto-parser.cpp # tests/test-chat.cpp # tests/test-llama-archs.cpp
This commit is contained in:
+36
-1
@@ -528,8 +528,43 @@ void common_models_handler_apply(common_models_handler & handler, common_params
|
||||
}
|
||||
};
|
||||
|
||||
// when a sidecar type is requested, the draft repo resolves to its sidecar instead of a full model
|
||||
const bool spec_sidecar_found = !plan_spec.mtp.local_path.empty() ||
|
||||
!plan_spec.dflash.local_path.empty() ||
|
||||
!plan_spec.eagle3.local_path.empty();
|
||||
if (!plan_spec.mtp.local_path.empty() && !had_spec_url) {
|
||||
tasks.emplace_back(plan_spec.mtp, opts, [&]() {
|
||||
// only use the discovered MTP head when no draft path is set yet
|
||||
if (params.speculative.draft.mparams.path.empty()) {
|
||||
params.speculative.draft.mparams.path = hf_cache::finalize_file(plan_spec.mtp);
|
||||
} else {
|
||||
hf_cache::finalize_file(plan_spec.mtp);
|
||||
}
|
||||
});
|
||||
}
|
||||
if (!plan_spec.dflash.local_path.empty() && !had_spec_url) {
|
||||
tasks.emplace_back(plan_spec.dflash, opts, [&]() {
|
||||
// only use the discovered DFlash sidecar when no draft path is set yet
|
||||
if (params.speculative.draft.mparams.path.empty()) {
|
||||
params.speculative.draft.mparams.path = hf_cache::finalize_file(plan_spec.dflash);
|
||||
} else {
|
||||
hf_cache::finalize_file(plan_spec.dflash);
|
||||
}
|
||||
});
|
||||
}
|
||||
if (!plan_spec.eagle3.local_path.empty() && !had_spec_url) {
|
||||
tasks.emplace_back(plan_spec.eagle3, opts, [&]() {
|
||||
// only use the discovered Eagle3 sidecar when no draft path is set yet
|
||||
if (params.speculative.draft.mparams.path.empty()) {
|
||||
params.speculative.draft.mparams.path = hf_cache::finalize_file(plan_spec.eagle3);
|
||||
} else {
|
||||
hf_cache::finalize_file(plan_spec.eagle3);
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
// handle plan_spec (e.g. --spec-draft-hf)
|
||||
if (!plan_spec.model_files.empty() && !had_spec_url) {
|
||||
if (!plan_spec.model_files.empty() && !had_spec_url && !spec_sidecar_found) {
|
||||
add_tasks(plan_spec.model_files, plan_spec.primary, params.speculative.draft.mparams);
|
||||
had_spec_url = true;
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user