Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	ci/README.md
#	ci/run.sh
#	docs/backend/CUDA-FEDORA.md
#	docs/build.md
#	docs/install.md
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cuda/common.cuh
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo
2025-03-26 00:18:01 +08:00
parent 2bdf1dacff 053b3f9aae
commit ea358369cc
26 changed files with 393 additions and 246 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-arch.cpp
+1
View File
@@ -778,6 +778,7 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
{
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" },
{ LLM_TENSOR_OUTPUT_NORM, "output_norm" },
{ LLM_TENSOR_OUTPUT, "output" },
{ LLM_TENSOR_ATTN_NORM, "blk.%d.attn_norm" },
{ LLM_TENSOR_ATTN_Q, "blk.%d.attn_q" },
{ LLM_TENSOR_ATTN_Q_NORM, "blk.%d.attn_q_norm" },
src/llama-context.cpp
+21 -4
View File
@@ -294,10 +294,7 @@ llama_context::llama_context(
// TODO: something cleaner
const auto n_outputs_save = n_outputs;
// max number of outputs
n_outputs = n_tokens;
LLAMA_LOG_DEBUG("%s: n_tokens = %d, n_seqs = %d, n_outputs = %d\n", __func__, n_tokens, n_seqs, n_outputs);
LLAMA_LOG_DEBUG("%s: worst-case: n_tokens = %d, n_seqs = %d, n_outputs = %d\n", __func__, n_tokens, n_seqs, n_outputs);
int n_splits_pp = -1;
int n_nodes_pp = -1;
@@ -313,8 +310,15 @@ llama_context::llama_context(
// reserve pp graph first so that buffers are only allocated once
{
llama_ubatch ubatch_pp = { true, n_tokens, n_tokens / n_seqs, n_seqs, &token, nullptr, nullptr, nullptr, nullptr, nullptr};
// max number of outputs
n_outputs = ubatch_pp.n_tokens;
LLAMA_LOG_DEBUG("%s: reserving graph for n_tokens = %d, n_seqs = %d\n", __func__, ubatch_pp.n_tokens, ubatch_pp.n_seqs);
auto * gf = graph_init();
graph_build(ctx_compute.get(), gf, ubatch_pp, LLM_GRAPH_TYPE_DEFAULT);
if (!ggml_backend_sched_reserve(sched.get(), gf)) {
throw std::runtime_error("failed to allocate compute pp buffers");
}
@@ -326,11 +330,18 @@ llama_context::llama_context(
// reserve with tg graph to get the number of splits and nodes
{
llama_ubatch ubatch_tg = { true, 1, 1, n_seqs, &token, nullptr, nullptr, nullptr, nullptr, nullptr};
n_outputs = ubatch_tg.n_tokens;
LLAMA_LOG_DEBUG("%s: reserving graph for n_tokens = %d, n_seqs = %d\n", __func__, ubatch_tg.n_tokens, ubatch_tg.n_seqs);
auto * gf = graph_init();
graph_build(ctx_compute.get(), gf, ubatch_tg, LLM_GRAPH_TYPE_DEFAULT);
if (!ggml_backend_sched_reserve(sched.get(), gf)) {
throw std::runtime_error("failed to allocate compute tg buffers");
}
n_splits_tg = ggml_backend_sched_get_n_splits(sched.get());
n_nodes_tg = ggml_graph_n_nodes(gf);
}
@@ -338,8 +349,14 @@ llama_context::llama_context(
// reserve again with pp graph to avoid ggml-alloc reallocations during inference
{
llama_ubatch ubatch_pp = { true, n_tokens, n_tokens / n_seqs, n_seqs, &token, nullptr, nullptr, nullptr, nullptr, nullptr};
n_outputs = ubatch_pp.n_tokens;
LLAMA_LOG_DEBUG("%s: reserving graph for n_tokens = %d, n_seqs = %d\n", __func__, ubatch_pp.n_tokens, ubatch_pp.n_seqs);
auto * gf = graph_init();
graph_build(ctx_compute.get(), gf, ubatch_pp, LLM_GRAPH_TYPE_DEFAULT);
if (!ggml_backend_sched_reserve(sched.get(), gf)) {
throw std::runtime_error("failed to allocate compute pp buffers");
}
src/llama-mmap.cpp
+1 -1
View File
@@ -480,7 +480,7 @@ struct llama_mlock::impl {
char* errmsg = std::strerror(errno);
bool suggest = (errno == ENOMEM);
#if defined(TARGET_OS_VISION) || defined(TARGET_OS_TV)
#if defined(TARGET_OS_VISION) || defined(TARGET_OS_TV) || defined(_AIX)
// visionOS/tvOS dont't support RLIMIT_MEMLOCK
// Skip resource limit checks on visionOS/tvOS
suggest = false;
src/llama-model.cpp
+6 -1
View File
@@ -2666,7 +2666,12 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
// output
output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED); // same as tok_embd, duplicated to allow offloading
output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
// if output is NULL, init from the input tok embed
if (output == NULL) {
output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
}
for (int i = 0; i < n_layer; ++i) {
auto & layer = layers[i];
src/llama-vocab.cpp
+10
View File
@@ -625,6 +625,12 @@ struct llm_tokenizer_bpe : llm_tokenizer {
"[^\\r\\n\\p{L}\\p{N}]?((?=[\\p{L}])([^a-z]))*((?=[\\p{L}])([^A-Z]))+(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])?|[^\\r\\n\\p{L}\\p{N}]?((?=[\\p{L}])([^a-z]))+((?=[\\p{L}])([^A-Z]))*(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])?|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n/]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
};
break;
case LLAMA_VOCAB_PRE_TYPE_SUPERBPE:
regex_exprs = {
"\\p{N}+",
"(?=(\\d{3})+(?!\\d))",
};
break;
default:
// default regex for BPE tokenization pre-processing
regex_exprs = {
@@ -1839,6 +1845,10 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
tokenizer_pre == "gpt-4o") {
pre_type = LLAMA_VOCAB_PRE_TYPE_GPT4O;
clean_spaces = false;
} else if (
tokenizer_pre == "superbpe") {
pre_type = LLAMA_VOCAB_PRE_TYPE_SUPERBPE;
clean_spaces = false;
} else {
throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
}