fix(tests): last two unguarded MXFP4 test helpers break plain CPU -Werror build - #62
Closed
localai-bot wants to merge 1 commit into
Closed
fix(tests): last two unguarded MXFP4 test helpers break plain CPU -Werror build#62localai-bot wants to merge 1 commit into
localai-bot wants to merge 1 commit into
Conversation
…4 — CPU -Werror repaired Same class as the test_linear_method fix: the #57 grouped-MoE test helpers are used only inside the VT_MARLIN_NVFP4 region (:804-:1446) but defined unguarded, failing the plain CPU-only Release -Werror build with unused-function at test_ops_moe_grouped.cpp:130/:173. A make -k sweep of the full suite confirms these are the LAST instances of the class. TU compiles clean after; no behavior change on any configuration that compiled before. FOLLOWING_AGENTS_PROTOCOL Assisted-by: Claude Code:claude-opus-4-8 [ClaudeCode]
Collaborator
Author
|
Landed on main as the squash (mudler authorship). 🤖 Generated with Claude Code |
mudler
added a commit
that referenced
this pull request
Aug 6, 2026
…4 — CPU -Werror repaired (#62) row/BUILD-CPU-WERROR-MOE-GROUPED-TESTFIX squash, companion to #61. The #57 grouped-MoE test helpers are used only inside the VT_MARLIN_NVFP4 region but defined unguarded, failing the plain CPU-only Release -Werror build at test_ops_moe_grouped.cpp:130/:173. A make -k sweep of the full suite confirms these are the LAST instances of the class. TU compiles clean after; no behavior change on any configuration that compiled before. FOLLOWING_AGENTS_PROTOCOL Assisted-by: Claude Code:claude-opus-4-8 [ClaudeCode]
mudler
added a commit
that referenced
this pull request
Aug 6, 2026
…ION lane lands (#26) feat/minimax-h3 squash (84 commits): the vLLM-Omni MiniMax-H3 33.1B CFG-distilled joint video+audio diffusion transformer, ported DERIVE-AND-SHIP. Packed fl2va/ref2va layout (fp64 position grid BIT-EXACT), euler-ancestral scheduler, 50-block AdaLN DiT forward (1.6e-7 vs upstream at reduced dims), BOTH VAEs reimplemented from the checkpoint's remote code (audio 4.2e-9, video ViT3D 8.9e-8), truncated Qwen3-VL encoder (1.2e-7), t2va/fl2va/ref2va pipelines, ComfyUI-GGUF + NVFP4 loaders, /v1/videos API logic, WAV/PPM/MP4-argv output, device- resident f32 forward GPU-VERIFIED on Thor sm_110. Attention routes through shared vt::DFlashBlockAttention(causal=false); projections through vt::MatmulBT; kMiniMaxH3 appended after main's landed enum ids. Merge resolutions: model-matrix keeps main's newer Laguna/kimi-k3 rows + both H3 rows (summary 359, engaged 45); pre-cutover BENCHMARKS sections rolled into the benchmark record; H3 STATUS row compacted to one in-budget cell with the full narrative preserved in state.md; ratchet paid by collapsing the superseded Laguna W7 block to a ledger pointer. Gate: clean full CPU -Werror build + full ctest on the merged tree (test_async_llm parallel-starve flake passes serially, the documented class). The two pre-existing plain-CPU -Werror breaks found by this gate landed separately as #61/#62. FOLLOWING_AGENTS_PROTOCOL Assisted-by: Claude Code:claude-opus-4-8 [ClaudeCode]
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
2 participants
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.
Companion to #61, same pre-existing class from #57: CheckCloseL2 + MakeMxfp4Weight used only under VT_MARLIN_NVFP4, defined unguarded. A make -k full-suite sweep confirms these are the last instances.
🤖 Generated with Claude Code
https://claude.ai/code/session_014fZAcg1WcU8V629k6HWKys