Skip to content

Fix/deepseek openai server #1071

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
charlesfrye merged 2 commits into from
Feb 11, 2025
Merged

Fix/deepseek openai server #1071

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a064656
Pin dependencies to specific versions for reproducibility
Feb 11, 2025
c573654
Update GPU type when build llama-cpp same with inference
Feb 11, 2025
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
26 changes: 13 additions & 13 deletions misc/deepseek_openai_server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,22 +113,22 @@
# Install all Python dependencies at once
.pip_install(
[
"fastapi",
"sse_starlette",
"pydantic",
"uvicorn[standard]",
"python-multipart",
"starlette-context",
"pydantic-settings",
"ninja",
"packaging",
"fastapi==0.115.8",
"sse_starlette==2.2.1",
"pydantic==2.10.6",
"uvicorn[standard]==0.34.0",
"python-multipart==0.0.20",
"starlette-context==0.3.6",
"pydantic-settings==2.7.1",
"ninja==1.11.1.3",
"packaging==24.2",
"wheel",
"torch",
]
"torch==2.6.0",
],
)
.run_commands(
'CMAKE_ARGS="-DGGML_CUDA=on" pip install llama-cpp-python',
gpu=modal.gpu.A10G(count=1),
gpu=modal.gpu.L40S(count=1),
)
.entrypoint([]) # remove NVIDIA base container entrypoint
)
Expand Down Expand Up @@ -231,7 +231,7 @@ def serve():
ModelSettings(
model=model_path, # Replace with your model path
n_gpu_layers=-1, # Use all GPU layers
n_ctx=8096 * 4,
n_ctx=8096,
n_batch=512,
n_threads=12,
verbose=True,
Expand Down
Loading