vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

replace deprecated

Browse source
This commit is contained in:
Concedo 2025-03-27 10:27:20 +08:00
parent 4bf675a83d
commit 6a709be50a
4 changed files with 6 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

2
expose.cpp
View file

@ -188,7 +188,7 @@ extern "C"
} }
else if(file_format==FileFormat::GGUF_GENERIC) else if(file_format==FileFormat::GGUF_GENERIC)
{ {
printf("\n---\nIdentified as GGUF model: (ver %d)\nAttempting to Load...\n---\n", file_format); printf("\n---\nIdentified as GGUF model.\nAttempting to Load...\n---\n", file_format);
} }
else if(file_format==FileFormat::GGML || file_format==FileFormat::GGHF || file_format==FileFormat::GGJT || file_format==FileFormat::GGJT_2 || file_format==FileFormat::GGJT_3) else if(file_format==FileFormat::GGML || file_format==FileFormat::GGHF || file_format==FileFormat::GGJT || file_format==FileFormat::GGJT_2 || file_format==FileFormat::GGJT_3)
{ {

4
gpttype_adapter.cpp
View file

@ -583,7 +583,7 @@ static void speculative_decoding_setup(std::string spec_model_filename, const ll
draft_ctx_params.type_v = base_ctx_params.type_v; draft_ctx_params.type_v = base_ctx_params.type_v;
llama_model * draftmodel = llama_model_load_from_file(spec_model_filename.c_str(), draft_model_params); llama_model * draftmodel = llama_model_load_from_file(spec_model_filename.c_str(), draft_model_params);
draft_ctx = llama_new_context_with_model(draftmodel, draft_ctx_params); draft_ctx = llama_init_from_model(draftmodel, draft_ctx_params);
if(draft_ctx == NULL) if(draft_ctx == NULL)
{ {
printf("Error: failed to load speculative decoding draft model '%s'\n", spec_model_filename.c_str()); printf("Error: failed to load speculative decoding draft model '%s'\n", spec_model_filename.c_str());
@ -2227,7 +2227,7 @@ ModelLoadResult gpttype_load_model(const load_model_inputs inputs, FileFormat in
llama_ctx_params.flash_attn = kcpp_data->flash_attn; llama_ctx_params.flash_attn = kcpp_data->flash_attn;
llama_ctx_params.type_k = (inputs.quant_k>1?GGML_TYPE_Q4_0:(inputs.quant_k==1?GGML_TYPE_Q8_0:GGML_TYPE_F16)); llama_ctx_params.type_k = (inputs.quant_k>1?GGML_TYPE_Q4_0:(inputs.quant_k==1?GGML_TYPE_Q8_0:GGML_TYPE_F16));
llama_ctx_params.type_v = (inputs.quant_v>1?GGML_TYPE_Q4_0:(inputs.quant_v==1?GGML_TYPE_Q8_0:GGML_TYPE_F16)); llama_ctx_params.type_v = (inputs.quant_v>1?GGML_TYPE_Q4_0:(inputs.quant_v==1?GGML_TYPE_Q8_0:GGML_TYPE_F16));
llama_ctx_v4 = llama_new_context_with_model(llamamodel, llama_ctx_params); llama_ctx_v4 = llama_init_from_model(llamamodel, llama_ctx_params);
if (llama_ctx_v4 == NULL) if (llama_ctx_v4 == NULL)
{ {

2
otherarch/embeddings_adapter.cpp
View file

@ -142,7 +142,7 @@ bool embeddingstype_load_model(const embeddings_load_model_inputs inputs)
ctx_params.n_threads_batch = nthreads; ctx_params.n_threads_batch = nthreads;
ctx_params.flash_attn = inputs.flash_attention; ctx_params.flash_attn = inputs.flash_attention;
embeddings_ctx = llama_new_context_with_model(embeddingsmodel, ctx_params); embeddings_ctx = llama_init_from_model(embeddingsmodel, ctx_params);
if (embeddings_ctx == nullptr) { if (embeddings_ctx == nullptr) {
printf("\nEmbeddings Model Load Error: Failed to initialize context!\n"); printf("\nEmbeddings Model Load Error: Failed to initialize context!\n");

4
otherarch/tts_adapter.cpp
View file

@ -542,7 +542,7 @@ bool ttstype_load_model(const tts_load_model_inputs inputs)
tts_ctx_params.flash_attn = inputs.flash_attention; tts_ctx_params.flash_attn = inputs.flash_attention;
llama_model * ttcmodel = llama_model_load_from_file(modelfile_ttc.c_str(), tts_model_params); llama_model * ttcmodel = llama_model_load_from_file(modelfile_ttc.c_str(), tts_model_params);
ttc_ctx = llama_new_context_with_model(ttcmodel, tts_ctx_params); ttc_ctx = llama_init_from_model(ttcmodel, tts_ctx_params);
if (ttc_ctx == nullptr) { if (ttc_ctx == nullptr) {
printf("\nTTS Load Error: Failed to initialize ttc context!\n"); printf("\nTTS Load Error: Failed to initialize ttc context!\n");
@ -552,7 +552,7 @@ bool ttstype_load_model(const tts_load_model_inputs inputs)
llama_model * ctsmodel = llama_model_load_from_file(modelfile_cts.c_str(), tts_model_params); llama_model * ctsmodel = llama_model_load_from_file(modelfile_cts.c_str(), tts_model_params);
tts_ctx_params.embeddings = true; //this requires embeddings instead tts_ctx_params.embeddings = true; //this requires embeddings instead
cts_ctx = llama_new_context_with_model(ctsmodel, tts_ctx_params); cts_ctx = llama_init_from_model(ctsmodel, tts_ctx_params);
if (cts_ctx == nullptr) { if (cts_ctx == nullptr) {
printf("\nTTS Load Error: Failed to initialize cts context!\n"); printf("\nTTS Load Error: Failed to initialize cts context!\n");