Repository navigation
docs(spec): the Flint port — CPU and GGUF arms (MODEL-TEXT-FLINT) - #3503
Merged
Merged
Conversation
Row declared with this spec. Scope, upstream anchors, design, risks, gates and owed items are in the spec; the issue records the same first wave. The reason this row exists now: the quantized artifacts are on disk and sha256-verified, llama.cpp's only flint support is an open PR from the model author (ggml-org/llama.cpp#30928, head 1b44e30775dcb2f93952116b05f89e5bd797f b00), vLLM has no flint code, and the peer (mistral.rs) has started a Flint implementation — so the architecture has a reference implementation to gate against and a second implementation to cross-check. FOLLOWING_AGENTS_PROTOCOL Following-Agents-Protocol: true AI-Assisted: true Assisted-by: AGENT:zai/glm-5.3-flash [maki]
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The row spec declaring
MODEL-TEXT-FLINT(RecursiveSI/flint,FlintForCausalLM, published 2026-10-21): the CPU and GGUF arms of a 49-layer hybrid-attention MoE with per-head attention sinks, an ungated shared expert, sigmoid routing and a no-RoPE full-attention pattern.Spec-first, per the row contract: this PR carries the spec and the issue only — no product code. The first wave it licenses is in the spec's Design section (the llama-cpp-flint oracle record at PR ggml-org/llama.cpp#30928's head, the model TU, and the flint GGUF loader row), with the Tenstorrent arm as a separate later row.
FOLLOWING_AGENTS_PROTOCOL
Following-Agents-Protocol: true
AI-Assisted: true
Assisted-by: AGENT:zai/glm-5.3-flash [maki]