mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-09-18 16:55:14 +02:00
Merge branch 'upstream' into concedo_experimental
# Conflicts: # README.md # docs/build-s390x.md # examples/llama.vim # ggml/src/ggml-cann/aclnn_ops.cpp # ggml/src/ggml-cann/common.h # scripts/compare-llama-bench.py # src/CMakeLists.txt # tests/test-backend-ops.cpp # tools/llama-bench/README.md # tools/llama-bench/llama-bench.cpp # tools/server/README.md
This commit is contained in:
+5
-3
@@ -1757,7 +1757,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
||||
[](common_params & params) {
|
||||
params.warmup = false;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_RETRIEVAL}));
|
||||
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_RETRIEVAL, LLAMA_EXAMPLE_PERPLEXITY}));
|
||||
add_opt(common_arg(
|
||||
{"--spm-infill"},
|
||||
string_format(
|
||||
@@ -2256,9 +2256,11 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
||||
).set_examples({LLAMA_EXAMPLE_PERPLEXITY}));
|
||||
add_opt(common_arg(
|
||||
{"-dt", "--defrag-thold"}, "N",
|
||||
string_format("KV cache defragmentation threshold (default: %.1f, < 0 - disabled)", (double)params.defrag_thold),
|
||||
string_format("KV cache defragmentation threshold (DEPRECATED)"),
|
||||
[](common_params & params, const std::string & value) {
|
||||
params.defrag_thold = std::stof(value);
|
||||
GGML_UNUSED(params);
|
||||
GGML_UNUSED(value);
|
||||
LOG_WRN("DEPRECATED: --defrag-thold is deprecated and no longer necessary to specify\n");
|
||||
}
|
||||
).set_env("LLAMA_ARG_DEFRAG_THOLD"));
|
||||
add_opt(common_arg(
|
||||
|
||||
Reference in New Issue
Block a user