thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

server : add custom socket options to disable SO_REUSEPORT (#21056)

Browse source 
* server : add custom socket options to disable SO_REUSEPORT

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Add --reuse-port

    $ strace -e trace=setsockopt,bind build/bin/llama-server -lv 2 --reuse-port
    setsockopt(3, SOL_TCP, TCP_NODELAY, [1], 4) = 0
    setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
    setsockopt(3, SOL_SOCKET, SO_REUSEPORT, [1], 4) = 0
    bind(3, {sa_family=AF_INET, sin_port=htons(8080), sin_addr=inet_addr("127.0.0.1")}, 16) = 0

    $ strace -e trace=setsockopt,bind build/bin/llama-server -lv 2
    setsockopt(3, SOL_TCP, TCP_NODELAY, [1], 4) = 0
    setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
    bind(3, {sa_family=AF_INET, sin_port=htons(8080), sin_addr=inet_addr("127.0.0.1")}, 16) = 0

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Update tools/server/README.md (llama-gen-docs)

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Fix windows

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

---------

Signed-off-by: Adrien Gallouët <angt@huggingface.co>
This commit is contained in:
Adrien Gallouët 2026-03-28 01:12:43 +01:00 • committed by GitHub
parent 59d840209a
commit 5c1a7b8355
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 25 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

7
common/arg.cpp
View file

@ -2807,6 +2807,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.port = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_PORT"));
add_opt(common_arg(
{"--reuse-port"},
string_format("allow multiple sockets to bind to the same port (default: %s)", params.reuse_port ? "enabled" : "disabled"),
[](common_params & params) {
params.reuse_port = true;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_REUSE_PORT"));
add_opt(common_arg(
{"--path"}, "PATH",
string_format("path to serve static files from (default: %s)", params.public_path.c_str()),

1
common/common.h
View file

@ -573,6 +573,7 @@ struct common_params {
// server params
int32_t port = 8080; // server listens on this network port
bool reuse_port = false; // allow multiple sockets to bind to the same port
int32_t timeout_read = 600; // http read timeout in seconds
int32_t timeout_write = timeout_read; // http write timeout in seconds
int32_t n_threads_http = -1; // number of threads to process HTTP requests (TODO: support threadpool)