Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-20 01:31:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

server: cleanup (remove slot.batch_spec, rename)

Browse Source
This commit is contained in:
Sascha Rogmann
2026-01-23 23:31:32 +01:00
parent 1e29af4ea5
commit a1584ac80f
11 changed files with 41 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/lookup/lookup-create.cpp
+2 -2
View File
@@ -32,9 +32,9 @@ int main(int argc, char ** argv){
common_ngram_cache ngram_cache;
common_ngram_cache_update(ngram_cache, LLAMA_NGRAM_STATIC, LLAMA_NGRAM_STATIC, inp, inp.size(), true);
fprintf(stderr, "%s: hashing done, writing file to %s\n", __func__, params.lookup_cache_static.c_str());
fprintf(stderr, "%s: hashing done, writing file to %s\n", __func__, params.speculative.lookup_cache_static.c_str());
common_ngram_cache_save(ngram_cache, params.lookup_cache_static);
common_ngram_cache_save(ngram_cache, params.speculative.lookup_cache_static);
return 0;
}
examples/lookup/lookup-stats.cpp
+5 -5
View File
@@ -46,18 +46,18 @@ int main(int argc, char ** argv){
{
const int64_t t_start_draft_us = ggml_time_us();
if (!params.lookup_cache_static.empty()) {
if (!params.speculative.lookup_cache_static.empty()) {
try {
ngram_cache_static = common_ngram_cache_load(params.lookup_cache_static);
ngram_cache_static = common_ngram_cache_load(params.speculative.lookup_cache_static);
} catch (std::ifstream::failure const &) {
LOG_ERR("failed to open static lookup cache: %s", params.lookup_cache_static.c_str());
LOG_ERR("failed to open static lookup cache: %s", params.speculative.lookup_cache_static.c_str());
exit(1);
}
}
if (!params.lookup_cache_dynamic.empty()) {
if (!params.speculative.lookup_cache_dynamic.empty()) {
try {
ngram_cache_dynamic = common_ngram_cache_load(params.lookup_cache_dynamic);
ngram_cache_dynamic = common_ngram_cache_load(params.speculative.lookup_cache_dynamic);
} catch (std::ifstream::failure const &) {} // if the file does not exist it will simply be created at the end of the program
}
examples/lookup/lookup.cpp
+6 -6
View File
@@ -51,18 +51,18 @@ int main(int argc, char ** argv){
const int64_t t_start_draft_us = ggml_time_us();
common_ngram_cache_update(ngram_cache_context, LLAMA_NGRAM_MIN, LLAMA_NGRAM_MAX, inp, inp.size(), false);
if (!params.lookup_cache_static.empty()) {
if (!params.speculative.lookup_cache_static.empty()) {
try {
ngram_cache_static = common_ngram_cache_load(params.lookup_cache_static);
ngram_cache_static = common_ngram_cache_load(params.speculative.lookup_cache_static);
} catch (std::ifstream::failure const &) {
LOG_ERR("failed to open static lookup cache: %s", params.lookup_cache_static.c_str());
LOG_ERR("failed to open static lookup cache: %s", params.speculative.lookup_cache_static.c_str());
exit(1);
}
}
if (!params.lookup_cache_dynamic.empty()) {
if (!params.speculative.lookup_cache_dynamic.empty()) {
try {
ngram_cache_dynamic = common_ngram_cache_load(params.lookup_cache_dynamic);
ngram_cache_dynamic = common_ngram_cache_load(params.speculative.lookup_cache_dynamic);
} catch (std::ifstream::failure const &) {} // if the file does not exist it will simply be created at the end of the program
}
@@ -210,7 +210,7 @@ int main(int argc, char ** argv){
// Update dynamic ngram cache with context ngram cache and save it to disk:
common_ngram_cache_merge(ngram_cache_dynamic, ngram_cache_context);
common_ngram_cache_save(ngram_cache_dynamic, params.lookup_cache_dynamic);
common_ngram_cache_save(ngram_cache_dynamic, params.speculative.lookup_cache_dynamic);
LOG("\n\n");
examples/speculative-simple/speculative-simple.cpp
+1 -1
View File
@@ -132,7 +132,7 @@ int main(int argc, char ** argv) {
params_spec.n_reuse = llama_n_ctx(ctx_dft) - n_draft;
params_spec.p_min = p_min;
struct common_speculative * spec = common_speculative_init(params, ctx_tgt, ctx_dft);
struct common_speculative * spec = common_speculative_init(params.speculative, ctx_tgt, ctx_dft);
for (auto &pair : params.speculative.replacements) {
common_speculative_add_replacement_tgt_dft(spec, pair.first.c_str(), pair.second.c_str());
}