mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

model: support MiMo-V2-Flash (#18328)

Browse Source 
* mimov2: convert ok

* rename mimov2 --> mimo2

* fix conversion

* runnable not incorrect

* use sink

* add_sliding_window_pattern

* add swa and per-layer n_head_kv

* correct params

* somewhat working

* correct gating func

* nits

* mimo2: wire RMS eps + MoE bias + converter guards

* add co-author

Co-authored-by: Aaryan-Kapoor <Aaryan-Kapoor@users.noreply.github.com>

* use add_rope_freq_base_swa

---------

Co-authored-by: Aaryan Kapoor <aaryankapoor2006@gmail.com>
Co-authored-by: Aaryan-Kapoor <Aaryan-Kapoor@users.noreply.github.com>
This commit is contained in:
Xuan-Son Nguyen
2025-12-24 23:07:08 +01:00
committed by GitHub
parent c184284230
commit 4cbafad4f0
11 changed files with 324 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-arch.cpp
+22
View File
@@ -115,6 +115,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
{ LLM_ARCH_RND1, "rnd1" },
{ LLM_ARCH_PANGU_EMBED, "pangu-embedded" },
{ LLM_ARCH_MISTRAL3, "mistral3" },
{ LLM_ARCH_MIMO2, "mimo2" },
{ LLM_ARCH_LLAMA_EMBED, "llama-embed" },
{ LLM_ARCH_UNKNOWN, "(unknown)" },
};
@@ -2190,6 +2191,27 @@ static std::set<llm_tensor> llm_get_tensor_names(llm_arch arch) {
LLM_TENSOR_VISEXP_FFN_DOWN,
LLM_TENSOR_VISEXP_FFN_UP,
};
case LLM_ARCH_MIMO2:
return {
LLM_TENSOR_TOKEN_EMBD,
LLM_TENSOR_OUTPUT_NORM,
LLM_TENSOR_OUTPUT,
LLM_TENSOR_ATTN_NORM,
LLM_TENSOR_ATTN_Q,
LLM_TENSOR_ATTN_K,
LLM_TENSOR_ATTN_V,
LLM_TENSOR_ATTN_SINKS,
LLM_TENSOR_ATTN_OUT,
LLM_TENSOR_FFN_NORM,
LLM_TENSOR_FFN_GATE,
LLM_TENSOR_FFN_DOWN,
LLM_TENSOR_FFN_UP,
LLM_TENSOR_FFN_GATE_INP,
LLM_TENSOR_FFN_GATE_EXPS,
LLM_TENSOR_FFN_DOWN_EXPS,
LLM_TENSOR_FFN_UP_EXPS,
LLM_TENSOR_FFN_EXP_PROBS_B,
};
case LLM_ARCH_GPTJ:
case LLM_ARCH_UNKNOWN:
return {