Skip to content

feat(server): passthrough proxy, piecewise keep-ratio curve, query survival check #294

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

Open
smpurkis wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat(server): passthrough proxy, piecewise keep-ratio curve, query survival check #294

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
5 changes: 3 additions & 2 deletions server/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -700,6 +700,7 @@ if(DFLASH27B_TESTS)

# ─── dflash_server: native C++ HTTP server ─────────────────────────
if(EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/src/server/server_main.cpp")
find_package(CURL REQUIRED)
add_executable(dflash_server
src/server/server_main.cpp
src/server/http_server.cpp
Expand All @@ -713,7 +714,7 @@ if(DFLASH27B_TESTS)
DFLASH27B_BACKEND_CUDA=1
DFLASH27B_CUDA_MIN_SM=${_dflash_cuda_min_sm})
endif()
target_link_libraries(dflash_server PRIVATE dflash_common ggml ${DFLASH27B_GGML_BACKEND_TARGET} pthread)
target_link_libraries(dflash_server PRIVATE dflash_common ggml ${DFLASH27B_GGML_BACKEND_TARGET} pthread CURL::libcurl)
if(DFLASH27B_GPU_BACKEND STREQUAL "cuda")
find_package(CUDAToolkit REQUIRED)
target_link_libraries(dflash_server PRIVATE CUDA::cudart)
Expand Down Expand Up @@ -780,7 +781,7 @@ if(DFLASH27B_TESTS)
DFLASH27B_BACKEND_CUDA=1
DFLASH27B_CUDA_MIN_SM=${_dflash_cuda_min_sm})
endif()
target_link_libraries(test_server_unit PRIVATE dflash_common ggml ${DFLASH27B_GGML_BACKEND_TARGET})
target_link_libraries(test_server_unit PRIVATE dflash_common ggml ${DFLASH27B_GGML_BACKEND_TARGET} CURL::libcurl)
if(DFLASH27B_GPU_BACKEND STREQUAL "cuda")
find_package(CUDAToolkit REQUIRED)
target_link_libraries(test_server_unit PRIVATE CUDA::cudart)
Expand Down
11 changes: 10 additions & 1 deletion server/src/qwen3/qwen3_drafter.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,7 +126,16 @@ bool load_drafter(const std::string & gguf_path, int /*gpu_layers*/,

bool load_drafter(const std::string & gguf_path, int /*gpu_layers*/,
int gpu, DrafterContext & out) {
return load_drafter(gguf_path, /*gpu_layers=*/999, DrafterArch::Qwen3_0p6b, gpu, out);
DrafterArch arch = DrafterArch::Qwen3_0p6b;
{
std::string lower = gguf_path;
for (auto & c : lower) c = (char)std::tolower((unsigned char)c);
if (lower.find("qwen3.5") != std::string::npos ||
lower.find("qwen35") != std::string::npos) {
arch = DrafterArch::Qwen35_0p8b;
}
}
return load_drafter(gguf_path, /*gpu_layers=*/999, arch, gpu, out);
}

bool load_drafter(const std::string & gguf_path, int /*gpu_layers*/,
Expand Down
Loading
Loading