summaryrefslogtreecommitdiff
path: root/common/common.h
diff options
context:
space:
mode:
authorRadoslav Gerganov <rgerganov@gmail.com>2024-05-14 14:27:19 +0300
committerGitHub <noreply@github.com>2024-05-14 14:27:19 +0300
commit5e31828d3e35c76ecfee665bc23771a4bec1d130 (patch)
tree7f5f2edc7c3fc3e7655904316897e32202edd5d6 /common/common.h
parent541600201e6480f54ae09e58d16b154d4b4b331d (diff)
ggml : add RPC backend (#6829)
* ggml : add RPC backend The RPC backend proxies all operations to a remote server which runs a regular backend (CPU, CUDA, Metal, etc). * set TCP_NODELAY * add CI workflows * Address review comments * fix warning * implement llama_max_devices() for RPC * Address review comments * Address review comments * wrap sockfd into a struct * implement get_alignment and get_max_size * add get_device_memory * fix warning * win32 support * add README * readme : trim trailing whitespace * Address review comments * win32 fix * Address review comments * fix compile warnings on macos
Diffstat (limited to 'common/common.h')
-rw-r--r--common/common.h1
1 files changed, 1 insertions, 0 deletions
diff --git a/common/common.h b/common/common.h
index d80344f2..566490e2 100644
--- a/common/common.h
+++ b/common/common.h
@@ -82,6 +82,7 @@ struct gpt_params {
float yarn_beta_slow = 1.0f; // YaRN high correction dim
int32_t yarn_orig_ctx = 0; // YaRN original context length
float defrag_thold = -1.0f; // KV cache defragmentation threshold
+ std::string rpc_servers = ""; // comma separated list of RPC servers
ggml_backend_sched_eval_callback cb_eval = nullptr;
void * cb_eval_user_data = nullptr;