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

Merge branch 'ggerganov:master' into sh-api-like-OAI

Browse source
This commit is contained in:
Yazan Agha-Schrader 2023-12-03 14:11:40 +01:00 • committed by GitHub
commit 83e211026d
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 4 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/server/api_like_OAI.py
View file

@ -70,6 +70,7 @@ def make_postData(body, chat=False, stream=False):
if(is_present(body, "mirostat_tau")): postData["mirostat_tau"] = body["mirostat_tau"]
if(is_present(body, "mirostat_eta")): postData["mirostat_eta"] = body["mirostat_eta"]
if(is_present(body, "seed")): postData["seed"] = body["seed"]
if(is_present(body, "grammar")): postData["grammar"] = body["grammar"]
if(is_present(body, "logit_bias")): postData["logit_bias"] = [[int(token), body["logit_bias"][token]] for token in body["logit_bias"].keys()]
if (args.stop != ""):
postData["stop"] = [args.stop]

4
examples/server/server.cpp
View file

@ -2410,9 +2410,7 @@ json oaicompat_completion_params_parse(
}
// Handle 'stop' field
if (body["stop"].is_null()) {
llama_params["stop"] = json::array({});
} else if (body["stop"].is_string()) {
if (body.contains("stop") && body["stop"].is_string()) {
llama_params["stop"] = json::array({body["stop"].get<std::string>()});
} else {
llama_params["stop"] = json_value(body, "stop", json::array());

2
ggml-metal.m
View file

@ -1083,7 +1083,7 @@ void ggml_metal_graph_compute(
// find the break-even point where the matrix-matrix kernel becomes more efficient compared
// to the matrix-vector kernel
int ne11_mm_min = 1;
int ne11_mm_min = src0t == GGML_TYPE_F16 ? 1 : 16;
#if 0
// the numbers below are measured on M2 Ultra for 7B and 13B models

3
llama.cpp
View file

@ -5744,8 +5744,7 @@ static int llama_decode_internal(
// a heuristic, to avoid attending the full cache if it is not yet utilized
// after enough generations, the benefit from this heuristic disappears
// if we start defragmenting the cache, the benefit from this will be more important
//kv_self.n = std::max(32, GGML_PAD(llama_kv_cache_cell_max(kv_self), 32)); // TODO: this might be better for CUDA?
kv_self.n = std::min((int32_t) cparams.n_ctx, std::max(32, llama_kv_cache_cell_max(kv_self)));
kv_self.n = std::min((int32_t) cparams.n_ctx, std::max(32, GGML_PAD(llama_kv_cache_cell_max(kv_self), 32)));
//printf("kv_self.n = %5d, kv_self.used = %5d, kv_self.head = %5d\n", kv_self.n, kv_self.used, kv_self.head);