2 Commits

Include renames

Author	SHA1	Message	Date
Gabe GoodhartandSigbjørn Skjæret	7221e24f57	model : GraniteSWAForCausalLM / GraniteMoeSWAForCausalLM (#25505) ... * feat(convert): Add conversion for GraniteSWAForCausalLM Branch: GraniteSWAForCausalLM AI-usage: full (Bob, OpenCode + Qwen3.6-35b) Signed-off-by: Gabe Goodhart <[email protected]> * feat(llama): Add granite_swa support Branch: GraniteSWAForCausalLM AI-usage: full (Bob, OpenCode + Qwen3.6-35b) Signed-off-by: Gabe Goodhart <[email protected]> * feat(conversion): Add conversion infra for rope_pattern array NOTE: There is other work also targeting this, so this may be removed depending on merge order. Branch: GraniteSWAForCausalLM AI-usage: full (Bob) Signed-off-by: Gabe Goodhart <[email protected]> * fix(conversion): Fix SWA pattern logic and support for non-rope layers Branch: GraniteSWAForCausalLM AI-usage: full (Bob) Signed-off-by: Gabe Goodhart <[email protected]> * feat(conversion): Add support for GraniteMoeSWA Branch: GraniteSWAForCausalLM AI-usage: full (Bob) Signed-off-by: Gabe Goodhart <[email protected]> * feat: Add llama_hparams::has_rope and arch constants NOTE: This shadows the work done for Granite Speech https://github.com/ggml-org/llama.cpp/pull/25107 Branch: GraniteSWAForCausalLM AI-usage: full (Bob) Signed-off-by: Gabe Goodhart <[email protected]> * feat: Add support for per-layer rope determination Branch: GraniteSWAForCausalLM AI-usage: full (Bob) Signed-off-by: Gabe Goodhart <[email protected]> * style: Fix failing flake8 for extra newlines Branch: GraniteSWAForCausalLM AI-usage: none Signed-off-by: Gabe Goodhart <[email protected]> * test: Write out SLIDING_WINDOW_PATTERN in llama-model-saver Branch: GraniteSWAForCausalLM AI-usage: full (OpenCode + Qwen3.6-35b) Signed-off-by: Gabe Goodhart <[email protected]> * fix(convert): Fix missing registration for GraniteMoeSWAForCausalLM Branch: GraniteSWAForCausalLM AI-usage: none Signed-off-by: Gabe Goodhart <[email protected]> * fix: Load MoE params as optional Branch: GraniteSWAForCausalLM AI-usage: draft (OpenCode + Qwen3.6-35b) Signed-off-by: Gabe Goodhart <[email protected]> * feat: Handle MoE params in conversion branch: GraniteSWAForCausalLM AI-usage: full (OpenCode + Qwen3.6-35b) Signed-off-by: Gabe Goodhart <[email protected]> * style: Remove unnecessary newline AI-usage: none Signed-off-by: Gabe Goodhart <[email protected]> * fix: Remove unnecessary tensor additions to GRANITE architecture Branch: GraniteSWAForCausalLM AI-usage: none Signed-off-by: Gabe Goodhart <[email protected]> * fix: Correctly handle naming for ffn gate inp Branch: GraniteSWAForCausalLM AI-usage: none Signed-off-by: Gabe Goodhart <[email protected]> * fix: Always default hparams.rope_pattern to 1s This isn't strictly necessary, but it will allow other models to rely on hparams.has_rope(il) without needting to prepopulate. Branch: GraniteSWAForCausalLM AI-usage: none Signed-off-by: Gabe Goodhart <[email protected]> * feat: Move to has_rope for all granite model architectures Now that we have a proper hparam for this, it's better to use it and not require a hacky fallback in the hparam method itself. Branch: GraniteSWAForCausalLM AI-usage: none Signed-off-by: Gabe Goodhart <[email protected]> * feat: No hacky rope_finetuned fallback in has_rope Branch: GraniteSWAForCausalLM AI-usage: none Signed-off-by: Gabe Goodhart <[email protected]> * fix: Fully remove rope hparam filling in granitemoe There are no granitemoe models that use NoPE (it's not actually used in the layer building below), so this was just dead code. Branch: GraniteSWAForCausalLM AI-usage: none Signed-off-by: Gabe Goodhart <[email protected]> * fix: Save out rope_pattern in model-saver Branch: GraniteSWAForCausalLM AI-usage: none Signed-off-by: Gabe Goodhart <[email protected]> * fix: Set hparams.rope_finetuned for round trip Since the value is _read_ from rope_finetuned, we need to persist it when the model is saved with the saver. Branch: GraniteSWAForCausalLM AI-usage: none Signed-off-by: Gabe Goodhart <[email protected]> * fix: Code review cleanup Signed-off-by: Gabe Goodhart <[email protected]> Co-authored-by: Sigbjørn Skjæret <[email protected]> Co-authored-by: Sigbjørn Skjæret <[email protected]> * refactor: Keep gate/up fused for MoE path Branch: GraniteSWAForCausalLM AI-usage: full (Claude + Sonnet 5) Signed-off-by: Gabe Goodhart <[email protected]> * fix: Skip GRANITE_SWA in model saver https://github.com/ggml-org/llama.cpp/pull/25505#discussion_r3773175651 Keeping is_swa_impl in the saver can break other models. Branch: GraniteSWAForCausalLM AI-usage: none Signed-off-by: Gabe Goodhart <[email protected]> * add sliding window pattern for model in test * style: Fix indentation Branch: GraniteSWAForCausalLM AI-usage: none Signed-off-by: Gabe Goodhart <[email protected]> * fix: Fix \r\n Thanks Claude! Branch: GraniteSWAForCausalLM AI-usage: none Signed-off-by: Gabe Goodhart <[email protected]> * feat: Keep shared expert fused Branch: GraniteSWAForCausalLM AI-usage: full (Claude + Sonnet 5) Signed-off-by: Gabe Goodhart <[email protected]> * style: More indentation fixes Signed-off-by: Gabe Goodhart <[email protected]> Co-authored-by: Sigbjørn Skjæret <[email protected]> --------- Signed-off-by: Gabe Goodhart <[email protected]> Co-authored-by: Sigbjørn Skjæret <[email protected]>	2026-08-19 16:53:31 +02:00
Bar Haim	157b81fe6d	model : Granite-Switch Architecture (#25107) ... * granite-switch: add llama.cpp backend (POC, CPU) New "granite-switch" architecture: a dense, all-attention Granite-4.1 model with N embedded LoRA adapters selected per-token by control tokens. - gguf-py schema (arch, KV keys, stacked LoRA tensor names) + writer helpers - conversion/granite.py: GraniteSwitchModel converter (stacks N adapters + zero base slot into per-projection A/B tensors; emits switch metadata) - C++ arch registration (llama-arch.{h,cpp}, llama-model.{h,cpp}) - src/models/granite_switch.cpp: load + per-token switched-LoRA graph via ggml_mul_mat_id over stacked tensors; sticky per-token index + control-token substitution in llm_graph_input_switch::set_input - llm_graph_input_switch in src/models/models.h Runs end-to-end on CPU: convert 3b checkpoint (842 tensors, stacked dim 13) and generate on both base and control-token paths. Sticky switch state is single-sequence (POC); full multi-sequence machinery is a follow-up. * granite-switch: add Mac (Metal) build + mid-sequence switch demo script Self-contained script to build llama.cpp on Apple Silicon (Metal), convert the composed 3b checkpoint, and run the crisp mid-sequence adapter-switch demos verified on Vela: - answerability: <|answerability|> mid-seq -> "unanswerable" - query_rewrite: <|query_rewrite|> mid-seq -> {"rewritten_question": ...} Each demo runs the same prompt twice, differing only by a control token placed before the assistant turn, so the per-token switch is visible. * granite-switch mac demo: add -no-cnv so each run is one-shot The composed model ships a chat template, so llama-completion auto-enables interactive conversation mode and halts at a `>` prompt after generating, stalling the script. -no-cnv disables conversation mode: generate once from the raw prompt and exit (also prints special tokens, making the switch visible). * granite-switch: replace global sticky index with in-graph router attention The POC computed the per-token adapter index on the CPU and carried it across ubatches in ONE global `mutable int32_t poc_sticky_index`, reset only when a ubatch contained sequence position 0. That global had two problems: 1. Concurrency: with multiple sequences in a batch it was last-writer- wins — one sequence's adapter leaked into the others. 2. Multi-turn: an interactive `ollama run` chat continues one KV cache, so turn 2 never saw position 0 and the index never reset — the adapter stayed stuck on across turns. Port the vLLM/HF backend mechanism faithfully: a single-head causal "router" attention recovers the adapter index in-graph. Per token, only dim 0 carries signal — Q[0]=1, K[0]=+gain for a control token / -gain otherwise, V[0]=adapter slot / 0 — and the causal softmax over the single visible control token recovers that adapter's slot (readback = clamp(round(V[0]), 0, n_adapters)). gain=15 matches config.py and is F16-safe (no F32 cache). The router's K/V live in the model KV cache at an extra layer R == hparams.router_layer (== n_layer). We bump n_layer_all to n_real+1 so the cache allocator gives the router its own per-sequence slot, and set n_layer_nextn=1 so n_layer() stays n_real — the decoder loop and tensor loading are untouched and never reference layer R. The router K is exempted from the k-shift RoPE loop (its dim-0 value is a literal magnitude, not a rotation). Because the selection now lives in the per-sequence KV cache, CONCURRENT requests are isolated for free (problem 1 fixed; verified by scratch/concurrent_switch_test.cpp). set_input becomes stateless pure per-token maps; the global is gone. Single-switch contract / known limitation, identical to vLLM & HF: the gain is flat (no recency), so within one sequence there is no mechanism to revert to base mid-sequence — once an adapter fires it stays on until that sequence ends (problem 2 is therefore NOT fixed by a faithful copy; vLLM/HF avoid it only because each served request is a fresh sequence). A client continuing one KV cache across turns must start a fresh sequence per turn, or opt into a recency-biased router (a deliberate divergence, not done here). Documented in granite_switch.cpp and asserted by scratch/multiturn_leak_test.cpp. Verified (CPU): both demos unchanged (answerability -> "unanswerable", query_rewrite -> rewritten query); concurrent two-sequence isolation passes; multi-turn carry-over matches the vLLM/HF contract. * granite-switch: drop scratch tests and mac demo for upstream PR Remove the local-only development artifacts that should not ship in the upstream PR: - granite-switch-mac-demo.sh (local Metal build + demo driver) - scratch/concurrent_switch_test.cpp - scratch/multiturn_leak_test.cpp Also drop the now-dangling reference to the scratch tests from the granite_switch.cpp header comment. Leaves only the core architecture support (conversion, gguf constants, llama-arch/model/kv-cache, and the granite_switch graph). * granite-switch: trim comments to match native llama.cpp style * granite-switch: trim conversion comments to match native style * granite-switch: drop unused adapter_ranks metadata * granite-switch: rename arch to graniteswitch and drop obid alias * granite-switch: fix non-ASCII comments and document router gain assumption * granite-switch: drop section comments from constants.py to match native style * granite-switch: add functional tensor block comments matching Granite4 Vision style * granite-switch: clarify n_expert_used comment State the actual constraint: mul_mat_id needs n_expert_used == 1, and since the GGUF carries expert_count = 0 the generic loader's n_expert == 0 => n_expert_used == 0 assertion has already passed by the time load_arch_hparams runs, so it is forced to 1 here. * granite-switch: note n_layer_nextn reuse has no MTP The router carving reuses n_layer_nextn, normally the MTP/next-token count. Clarify in the comment that it is borrowed here purely as the trailing-layers lever and that there is no MTP head, to spare readers the double-take. * granite-switch: rename source file and apply review nits * granite-switch: don't force LoRA tensors to F16, follow --outtype instead * granite-switch: drop redundant _permute_qk wrapper, call LlamaModel.permute directly * granite-switch: read router gain from GGUF (control_token_gain) instead of hardcoding 15.0 * granite-switch: derive n_slots() * granite-switch: move llm_graph_input_switch into granite-switch.cpp * granite-switch: cut AI-style narration comments * granite-switch: collapse multi-line comments * granite-switch: rename control_token_* maps to adapter_token_* * granite-switch: cut noise comments * granite-switch: rename embedded LoRA tensors to <base>.lora_a/lora_b * granite-switch: GGML_ASSERT token input to avoid UB on embeddings * granite-switch: TODO for raw embedding input support * granite-switch: collapse LoRA tensor constants to .lora_a/.lora_b suffix * granite-switch: drop n_expert_used hack, guard mul_mat_id buft probe * granite-switch: stop forcing dense expert counts, read from config * granite-switch: renamed control_token_gain metadata key to router_gain * granite-switch: trim header comments to match native style * granite-switch: collapse LoRA tensors to base name + suffix * granite-switch: inline suffix checks in tensor op resolution * granite-switch: drop switch-lora struct comment * granite-switch: guard router layer index and inline n_slots * granite-switch: group adapter metadata under {arch}.adapters.* namespace * granite-switch: add hparams.has_rope(il) for KV-shift rope skipping * granite-switch: skip arch in test-llama-archs (adapter fixture missing, TODO) * granite-switch: Keys.Adapters namespace + simplify n_slots * granite-switch: validate substitute token ids against n_vocab * granite-switch: bound adapter count and lora rank from GGUF * granite-switch: reject MTP context type when router_layer is set * granite-switch: throw on bad adapter metadata instead of GGML_ASSERT * granite-switch: use ASCII +/- in router K signal comment * granite-switch: document n_layer_nextn repurpose and its leak points * granite-switch: gate lora_a/lora_b op mapping on router_layer * granite-switch: label all three preview model sizes	2026-08-10 09:53:46 +02:00