Skip to content

fix: adapt llama-server to current xllamacpp binding #307

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
WSHAPER merged 1 commit into from
Oct 19, 2026
+8 −5
Merged

fix: adapt llama-server to current xllamacpp binding #307

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 7 additions & 4 deletions lib/llama_server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@
"n_gpu_layers", "main_gpu", "split_mode", "tensor_split",
"no_kv_offload", "no_op_offload", "flash_attn_type",
# Memory
"use_mmap", "use_mlock",
"cache_type_k", "cache_type_v",
"cache_prompt", "cache_idle_slots", "cache_ram_mib",
# RoPE / YaRN
Expand All @@ -32,7 +31,7 @@
"reasoning_format", "enable_reasoning",
"use_jinja", "chat_template", "enable_chat_template",
# Server
"hostname", "port", "n_threads_http",
"hostnames", "port", "n_threads_http",
"timeout_read", "timeout_write",
"api_keys", "api_prefix",
# Misc
Expand All @@ -49,8 +48,12 @@ def main() -> None:
if cfg.get("mmproj_path"):
p.mmproj.path = cfg["mmproj_path"]
for k in SERVER_KEYS:
if k in cfg:
setattr(p, k, cfg[k])
if k not in cfg:
continue
if not hasattr(p, k):
print(f"llama_server: ignoring server key '{k}' (not supported by this xllamacpp)", file=sys.stderr)
continue
setattr(p, k, cfg[k])

server = xlc.Server(p) # noqa: F841 — held to keep the C++ server thread alive
while True:
Expand Down
2 changes: 1 addition & 1 deletion lib/task_processors.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -150,7 +150,7 @@ def generate_chat_model(file_name: str) -> ChatOpenAI:

server_cfg: dict = {
"model_path": path,
"hostname": "127.0.0.1",
"hostnames": ["127.0.0.1"],
"port": port,
"n_gpu_layers": n_gpu_layers,
"n_batch": loader_config.get("n_batch", 512),
Expand Down
Loading