vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Updated arg.cpp instead of auto-generated README.md

Browse source
This commit is contained in:
MichelleTPY 2024-12-12 19:32:39 +00:00
parent 59940ef310
commit 92a9392fcd
2 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

4
common/arg.cpp
View file

@ -1174,7 +1174,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_env("LLAMA_ARG_NO_KV_OFFLOAD"));
add_opt(common_arg(
{"-ctk", "--cache-type-k"}, "TYPE",
string_format("KV cache data type for K (default: %s)", params.cache_type_k.c_str()),
string_format("KV cache data type for K : f16, f32, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1 (default: %s)", params.cache_type_k.c_str()),
[](common_params & params, const std::string & value) {
// TODO: get the type right here
params.cache_type_k = value;
@ -1182,7 +1182,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_env("LLAMA_ARG_CACHE_TYPE_K"));
add_opt(common_arg(
{"-ctv", "--cache-type-v"}, "TYPE",
string_format("KV cache data type for V (default: %s)", params.cache_type_v.c_str()),
string_format("KV cache data type for V : : f16, f32, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1 (default: %s)", params.cache_type_v.c_str()),
[](common_params & params, const std::string & value) {
// TODO: get the type right here
params.cache_type_v = value;

4
examples/server/README.md
View file

@ -62,8 +62,8 @@ The project is under active development, and we are [looking for feedback and co
| `--yarn-beta-fast N` | YaRN: low correction dim or beta (default: 32.0)<br/>(env: LLAMA_ARG_YARN_BETA_FAST) |
| `-dkvc, --dump-kv-cache` | verbose print of the KV cache |
| `-nkvo, --no-kv-offload` | disable KV offload<br/>(env: LLAMA_ARG_NO_KV_OFFLOAD) |
| `-ctk, --cache-type-k TYPE` | KV cache data type for K (default: f16, f32, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1)<br/>(env: LLAMA_ARG_CACHE_TYPE_K) |
| `-ctv, --cache-type-v TYPE` | KV cache data type for V (default: f16, f32, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1)<br/>(env: LLAMA_ARG_CACHE_TYPE_V) |
| `-ctk, --cache-type-k TYPE` | KV cache data type for K (default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_K) |
| `-ctv, --cache-type-v TYPE` | KV cache data type for V (default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_V) |
| `-dt, --defrag-thold N` | KV cache defragmentation threshold (default: 0.1, < 0 - disabled)<br/>(env: LLAMA_ARG_DEFRAG_THOLD) |
| `-np, --parallel N` | number of parallel sequences to decode (default: 1)<br/>(env: LLAMA_ARG_N_PARALLEL) |
| `--mlock` | force system to keep model in RAM rather than swapping or compressing<br/>(env: LLAMA_ARG_MLOCK) |