mudler / mudler/vllm.cpp

Metal build fails: unused const kGdnLayers in test_qwen27n_fp8_tower_paged_engine.cpp

Open Beginner friendly
#629 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
423
Forks
53
Avg merge
20h 26m
Merged PRs (30d)
310

Description

tests/parity/test_qwen27n_fp8_tower_paged_engine.cpp:95 declares constexpr uint64_t kGdnLayers = 48; unconditionally, but its only uses (lines 281, 282, 329) sit inside #ifdef VLLM_CPP_CUDA.

On a non-CUDA build (cmake -DVLLM_CPP_MLX=ON Metal configure on macOS) this trips -Werror,-Wunused-const-variable and breaks the build at 100%:

tests/parity/test_qwen27n_fp8_tower_paged_engine.cpp:95:20: error: unused variable 'kGdnLayers' [-Werror,-Wunused-const-variable]

Fix: move the constant (and its comment) inside the same #ifdef VLLM_CPP_CUDA guard as its uses.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Open tests/parity/test_qwen27n_fp8_tower_paged_engine.cpp and inspect the kGdnLayers declaration at line 95 alongside its CUDA-only uses around lines 281, 282, and 329. Move the constant and its comment under the VLLM_CPP_CUDA guard, then configure with cmake -DVLLM_CPP_MLX=ON to confirm the non-CUDA Metal build completes without the unused-variable error.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
build-system
Issue type
Bug
Difficulty
1/5
Estimated time
Under an hour
Activity status
Quiet
Clarity
Clearly specified
Newbie friendliness
92/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.