feat(model-ports): add granite4_h_micro - #209
Open
DarthCeltic wants to merge 3 commits into
Open
Conversation
Full compliant shape (claim + framework registration + real host-CPU perplexity). Built a plain CPU-only (GGML_ET=OFF) llama-perplexity from the vendored source, ran against the board-pinned WikiText-2 corpus. Loads and scores cleanly (PPL 13.2058), allocating both a small transformer KV cache (4 layers) and a larger recurrent SSM state cache (40 layers) -- IBM's fourth-gen Granite hybrid architecture, arch=granitehybrid, distinct from both dense granite and granitemoe already on this board. Third SSM/hybrid data point this campaign (after mamba_1_4b, falcon_h1_1_5b). Also checked falcon-mamba-7b-instruct: resolves to plain arch=mamba, not a distinct family -- same execution family as mamba_1_4b already claimed, so no additional claim filed for it (same pattern as baichuan2/internlm3 resolving to llama earlier in this campaign).
github-actions
Bot
added
track: model-ports
DarthCeltic
added a commit
to DarthCeltic/hf-hackathon
that referenced
this pull request
Jul 25, 2026
…_micro Each claim's benchmark_config must exactly match the model's "config" pointer in .github/ci/benchmark_config.json per effective_model_config() in model_port_claim.py, not the top-level benchmark_config.json path itself. Fixes a mismatch that would fail eligibility validation.
Member
|
For Granite4-H model-port credit, please add a committed deterministic oracle/expected output and a successful full-offload ET-SoC1 run, not only host loading/PPL. After that evidence passes review, maintainers still need to adopt the execution-family identity/contract and approve the |
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.
Adds granite4_h_micro causal-LM port to llama.cpp-et, with a model-ports claim.