Repository navigation
Conversation
- tests: the tiny DeepSeek-V3 uses as many key/value heads as query heads, as multi-head latent attention does (Linux CPU SDPA rejected 2). - serve loads and checks the model before importing uvicorn, so model errors such as UnsupportedBackend come first; dev installs uvicorn.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
CI failed on main after #1 with two test-side issues:
test_zoo[deepseek_v3]: the tiny config gave DeepSeek-V3 2 key/value heads, but multi-head latent attention uses as many key/value heads as query heads. Linux's CPU SDPA rejected it (macOS didn't), so the test now uses 4.test_serve_command_reports_unsupported_backend:serveimported uvicorn before loading the model, and CI'sdevextra has no uvicorn.servenow loads and checks the model first, anddevincludes uvicorn.Verified on Linux (Python 3.12, torch 2.14.1, uvicorn not installed): zoo and vLLM-backend tests pass (55). The full suite passes locally (263).