Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/kleidiai/kernels.cpp
#	ggml/src/ggml-cpu/kleidiai/kernels.h
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-cpu/ops.cpp
#	ggml/src/ggml-cuda/mmq.cuh
#	ggml/src/ggml-hexagon/htp/hmx-queue.c
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_iq4_nl_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q1_0_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q4_0_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q4_0_f32_spec.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q4_1_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q4_k_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q5_0_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q5_1_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q5_k_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q6_k_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q8_0_f32.cl
#	ggml/src/ggml-opencl/kernels/mul_mv_f16_f16.cl
#	ggml/src/ggml-opencl/kernels/mul_mv_f16_f32.cl
#	ggml/src/ggml-opencl/kernels/mul_mv_f16_f32_1row.cl
#	ggml/src/ggml-sycl/fattn-vec.hpp
#	tests/test-backend-ops.cpp
#	tests/test-chat-auto-parser.cpp
#	tests/test-export-graph-ops.cpp
#	tests/test-jinja.cpp
#	tests/test-llama-archs.cpp
#	tools/tokenize/tokenize.cpp
This commit is contained in:
Concedo
2026-07-15 15:39:31 +08:00
73 changed files with 6859 additions and 3973 deletions
+65 -1
View File
@@ -91,7 +91,7 @@ def test_openai_library_correct_api_key():
("localhost", "Access-Control-Allow-Origin", "localhost"),
("web.mydomain.fr", "Access-Control-Allow-Origin", "web.mydomain.fr"),
("origin", "Access-Control-Allow-Credentials", "true"),
("web.mydomain.fr", "Access-Control-Allow-Methods", "GET, POST"),
("web.mydomain.fr", "Access-Control-Allow-Methods", "GET, POST, DELETE, OPTIONS"),
("web.mydomain.fr", "Access-Control-Allow-Headers", "*"),
])
def test_cors_options(origin: str, cors_header: str, cors_header_value: str):
@@ -107,6 +107,70 @@ def test_cors_options(origin: str, cors_header: str, cors_header_value: str):
assert res.headers[cors_header] == cors_header_value
@pytest.mark.parametrize("origin", [
"http://localhost",
"http://localhost:8080",
"http://127.0.0.1",
"http://127.0.0.1:3000",
"http://[::1]",
"http://[::1]:3000",
])
def test_cors_origins_localhost_reflects(origin: str):
global server
server = ServerPreset.router()
server.cors_origins = "localhost"
server.start()
res = server.make_request("OPTIONS", "/completions", headers={
"Origin": origin,
"Access-Control-Request-Method": "POST",
"Access-Control-Request-Headers": "Authorization",
})
assert res.status_code == 200
assert res.headers["Access-Control-Allow-Origin"] == origin
@pytest.mark.parametrize("origin", [
"http://web.mydomain.fr",
"http://evil.com",
"http://notlocalhost",
"http://localhost.evil.com",
])
def test_cors_origins_localhost_rejects(origin: str):
global server
server = ServerPreset.router()
server.cors_origins = "localhost"
server.start()
res = server.make_request("OPTIONS", "/completions", headers={
"Origin": origin,
"Access-Control-Request-Method": "POST",
"Access-Control-Request-Headers": "Authorization",
})
assert res.status_code == 200
assert "Access-Control-Allow-Origin" not in res.headers
def test_cors_origins_defaults_to_localhost_with_tools_enabled():
global server
server = ServerPreset.router()
server.server_tools = "all"
server.start()
res = server.make_request("OPTIONS", "/completions", headers={
"Origin": "http://localhost:8080",
"Access-Control-Request-Method": "POST",
"Access-Control-Request-Headers": "Authorization",
})
assert res.status_code == 200
assert res.headers["Access-Control-Allow-Origin"] == "http://localhost:8080"
res = server.make_request("OPTIONS", "/completions", headers={
"Origin": "http://evil.com",
"Access-Control-Request-Method": "POST",
"Access-Control-Request-Headers": "Authorization",
})
assert res.status_code == 200
assert "Access-Control-Allow-Origin" not in res.headers
def test_cors_proxy_only_forwards_explicit_proxy_headers():
class CaptureHeadersHandler(BaseHTTPRequestHandler):
def do_GET(self):
+4 -1
View File
@@ -114,6 +114,7 @@ class ServerProcess:
backend_sampling: bool = False
gcp_compat: bool = False
server_tools: str | None = None
cors_origins: str | None = None
# session variables
process: subprocess.Popen | None = None
@@ -170,6 +171,8 @@ class ServerProcess:
server_args.extend(["--models-max", self.models_max])
if self.models_preset:
server_args.extend(["--models-preset", self.models_preset])
if self.cors_origins:
server_args.extend(["--cors-origins", self.cors_origins])
if self.n_batch:
server_args.extend(["--batch-size", self.n_batch])
if self.n_ubatch:
@@ -359,7 +362,7 @@ class ServerProcess:
if parse_body:
try:
result.body = response.json()
except JSONDecodeError:
except (JSONDecodeError, requests.exceptions.JSONDecodeError):
result.body = response.text
else:
result.body = None