Bump candle rev to 7de0d9fd (picks up moe_gemm_wmma rename to avoid symbol collision)#22
Merged
Merged
Conversation
Picks up spiceai/candle#13 which renames candle-kernels' moe_gemm_wmma -> candle_moe_gemm_wmma so it no longer collides with mistralrs-core's identically-named but semantically divergent kernel when both crates are linked together (e.g. in spiced --features cuda,models).
lukekim
added a commit
to spiceai/spiceai
that referenced
this pull request
Apr 17, 2026
Resolves ld.lld duplicate-symbol link error when building spiced with
cuda + models features:
ld.lld: error: duplicate symbol: moe_gemm_wmma
>>> defined in libmoe.a (candle-kernels)
>>> defined in libmistralrscuda.a (mistralrs-core)
Three coordinated fork PRs:
- spiceai/candle#13: rename moe_gemm_wmma -> candle_moe_gemm_wmma
in candle-kernels so it no longer collides with mistralrs-core's
identically-named but semantically divergent kernel.
- spiceai/mistral.rs#34: bump candle rev to 7de0d9fd.
- spiceai/text-embeddings-inference#22: bump candle rev to 7de0d9fd.
New workspace pins:
- candle fab4da81 -> 7de0d9fd
- mistralrs 9b475876 -> b93f7600
- text-embeddings b958dca5 -> bd66a55d
Verified with make install-cuda on CUDA 12.6 / sm_90 (H100): links
and installs cleanly in 18m51s.
krinart
approved these changes
Apr 17, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Bumps the
candlerev fromc87b9bc5to7de0d9fdto pick up spiceai/candle#13, which renames candle-kernels'moe_gemm_wmma→candle_moe_gemm_wmma.Why
candle-kernels and mistralrs-core each independently export an
extern "C" void moe_gemm_wmmakernel (both adapted from guoqingbao/attention.rs but with diverged signatures and implementations). When a binary links both — e.g.spiced --features cuda,modelspulls in bothtext-embeddings-backend-candleandmistralrs-core—ld.lldrejects the duplicate symbol:Picking up the rename on the candle side resolves it; TEI itself needs no source changes.
Scope
Cargo.toml: candle rev bumped in the root[workspace.dependencies]block.Verification
Verified
spiced --features cuda,modelslinks cleanly on CUDA 12.6 / sm_90 (H100) with the matching spiceai/spiceai pin bump.