Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-08 05:49:10 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	requirements/requirements-convert_hf_to_gguf_update.txt
#	scripts/compare-llama-bench.py
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tools/imatrix/README.md
#	tools/imatrix/imatrix.cpp
#	tools/llama-bench/llama-bench.cpp
This commit is contained in:
Concedo
2025-08-04 22:42:02 +08:00
parent d37529c0cd 5aa1105da2
commit 8bd0a560f0
23 changed files with 512 additions and 210 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+2
View File
@@ -904,6 +904,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
} break;
case LLM_ARCH_QWEN3:
{
ml.get_key(LLM_KV_POOLING_TYPE, hparams.pooling_type, false);
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
switch (hparams.n_layer) {
case 28: type = hparams.n_embd == 1024 ? LLM_TYPE_0_6B : LLM_TYPE_1_7B; break;
@@ -17697,6 +17698,7 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params,
/* recurrent_kv_size */ std::max((uint32_t) 1, cparams.n_seq_max),
/* n_seq_max */ cparams.n_seq_max,
/* offload */ cparams.offload_kqv,
/* unified */ cparams.kv_unified,
/* filter_attn */ (arch == LLM_ARCH_FALCON_H1) ? [&](int32_t) { return true; } : (llama_memory_hybrid::layer_filter_cb)nullptr,
/* filter_recr */ (arch == LLM_ARCH_FALCON_H1) ? [&](int32_t) { return true; } : (llama_memory_hybrid::layer_filter_cb)nullptr);
} else {