mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-08-24 15:56:12 +00:00
3733366720
* Adding support for bailingmoe3
* Adds speculative decoding support
* Make BailingMoE3 safe gate metadata optional
* bailingmoe3: apply trained SwiGLU clamps
* common: fix Bailing V3 tool argument parsing
* llama-model-saver, instantiate float vector metadata writer
* bailingmoe3: support Q-LoRA (Ling-3.0-tiny)
Ling-3.0-flash sets q_lora_rank: None and projects Q directly, so the current
implementation loads a single ATTN_Q tensor. Ling-3.0-tiny sets q_lora_rank: 256
and routes Q through a LoRA bottleneck instead:
q_a_proj -> q_a_layernorm -> q_b_proj
Conversion therefore failed with:
ValueError: Can not map tensor 'model.layers.3.attention.q_a_layernorm.weight'
Add the missing path, mirroring the existing deepseek2 MLA implementation:
* constants.py - add ATTN_Q_A / ATTN_Q_B / ATTN_Q_A_NORM to BAILINGMOE3
* tensor_mapping.py - map model.layers.{bid}.attention.q_{a,b}_proj and
q_a_layernorm
* conversion - emit attention.q_lora_rank when the config has it
* bailingmoe3.cpp - read n_lora_q; create the Q-LoRA tensors and build Q
through the bottleneck when q_lora_rank > 0
Everything is gated on q_lora_rank > 0. Ling-3.0-flash's config has no
q_lora_rank, the converter only emits the key when present, hparams.n_lora_q
defaults to 0, and get_key(..., required=false) leaves the target untouched when
the key is absent - so flash keeps taking the existing direct-Q branch.
The LoRA path produces the same shape as the direct projection, so the
nope/rope split, RoPE application and wk_b absorption downstream are unchanged.
* small mtp change
* bailingmoe3: support separate MTP GGUF and Q-LoRA MTP
* gguf: remove duplicate add_kda_gate_lower_bound definition
---------
Co-authored-by: bloomer <bloomer@booper.brushtail.me>
Co-authored-by: Dyluhn <dylanranejohnston1@gmail.com>
|
||
|---|---|---|
| .. | ||
| jinja | ||
| arg.cpp | ||
| arg.h | ||
| base64.hpp | ||
| build-info.cpp.in | ||
| build-info.h | ||
| chat-auto-parser-generator.cpp | ||
| chat-auto-parser-helpers.cpp | ||
| chat-auto-parser-helpers.h | ||
| chat-auto-parser.h | ||
| chat-diff-analyzer.cpp | ||
| chat-peg-parser.cpp | ||
| chat-peg-parser.h | ||
| chat.cpp | ||
| chat.h | ||
| CMakeLists.txt | ||
| common.cpp | ||
| common.h | ||
| console.cpp | ||
| console.h | ||
| debug.cpp | ||
| debug.h | ||
| download.cpp | ||
| download.h | ||
| fit.cpp | ||
| fit.h | ||
| hf-cache.cpp | ||
| hf-cache.h | ||
| http.h | ||
| imatrix-loader.cpp | ||
| imatrix-loader.h | ||
| json-schema-to-grammar.cpp | ||
| json-schema-to-grammar.h | ||
| llguidance.cpp | ||
| log.cpp | ||
| log.h | ||
| ngram-cache.cpp | ||
| ngram-cache.h | ||
| ngram-map.cpp | ||
| ngram-map.h | ||
| ngram-mod.cpp | ||
| ngram-mod.h | ||
| peg-parser.cpp | ||
| peg-parser.h | ||
| preset.cpp | ||
| preset.h | ||
| reasoning-budget.cpp | ||
| reasoning-budget.h | ||
| sampling.cpp | ||
| sampling.h | ||
| speculative.cpp | ||
| speculative.h | ||
| subproc.cpp | ||
| subproc.h | ||
| trie.cpp | ||
| trie.h | ||
| unicode.cpp | ||
| unicode.h | ||