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:
#	CMakePresets.json
#	Makefile
#	Package.swift
#	ci/run.sh
#	common/CMakeLists.txt
#	examples/CMakeLists.txt
#	flake.lock
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-backend.cpp
#	ggml/src/ggml.c
#	pocs/vdot/q8dot.cpp
#	pocs/vdot/vdot.cpp
#	tests/test-backend-ops.cpp
#	tests/test-grad0.cpp
#	tests/test-quantize-fns.cpp
#	tests/test-quantize-perf.cpp
#	tests/test-rope.cpp
This commit is contained in:
Concedo
2024-11-04 16:54:53 +08:00
parent c7e351bf41 9f40989351
commit bb13925f39
34 changed files with 14917 additions and 19458 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama.cpp
+22 -6
View File
@@ -19524,12 +19524,26 @@ struct llama_context * llama_new_context_with_model(
cparams.causal_attn = params.attention_type == LLAMA_ATTENTION_TYPE_CAUSAL;
}
LLAMA_LOG_INFO("%s: n_ctx = %u\n", __func__, cparams.n_ctx);
LLAMA_LOG_INFO("%s: n_batch = %u\n", __func__, cparams.n_batch);
LLAMA_LOG_INFO("%s: n_ubatch = %u\n", __func__, cparams.n_ubatch);
LLAMA_LOG_INFO("%s: flash_attn = %d\n", __func__, cparams.flash_attn);
LLAMA_LOG_INFO("%s: freq_base = %.1f\n", __func__, cparams.rope_freq_base);
LLAMA_LOG_INFO("%s: freq_scale = %g\n", __func__, cparams.rope_freq_scale);
const uint32_t n_ctx_per_seq = cparams.n_ctx / cparams.n_seq_max;
LLAMA_LOG_INFO("%s: n_seq_max = %u\n", __func__, cparams.n_seq_max);
LLAMA_LOG_INFO("%s: n_ctx = %u\n", __func__, cparams.n_ctx);
LLAMA_LOG_INFO("%s: n_ctx_per_seq = %u\n", __func__, n_ctx_per_seq);
LLAMA_LOG_INFO("%s: n_batch = %u\n", __func__, cparams.n_batch);
LLAMA_LOG_INFO("%s: n_ubatch = %u\n", __func__, cparams.n_ubatch);
LLAMA_LOG_INFO("%s: flash_attn = %d\n", __func__, cparams.flash_attn);
LLAMA_LOG_INFO("%s: freq_base = %.1f\n", __func__, cparams.rope_freq_base);
LLAMA_LOG_INFO("%s: freq_scale = %g\n", __func__, cparams.rope_freq_scale);
if (n_ctx_per_seq < hparams.n_ctx_train) {
LLAMA_LOG_WARN("%s: n_ctx_per_seq (%u) < n_ctx_train (%u) -- the full capacity of the model will not be utilized\n",
__func__, n_ctx_per_seq, hparams.n_ctx_train);
}
if (n_ctx_per_seq > hparams.n_ctx_train) {
LLAMA_LOG_WARN("%s: n_ctx_pre_seq (%u) > n_ctx_train (%u) -- possible training context overflow\n",
__func__, n_ctx_per_seq, hparams.n_ctx_train);
}
ctx->abort_callback = params.abort_callback;
ctx->abort_callback_data = params.abort_callback_data;
@@ -21980,6 +21994,8 @@ int llama_split_prefix(char * dest, size_t maxlen, const char * split_path, int
}
const char * llama_print_system_info(void) {
ggml_cpu_init(); // some ARM features are detected at runtime
static std::string s;
s = "";