Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

model: add dots3-note (#27060)

Browse Source 
* text: conversion

* init impl

* address review comments

* fix rope

* move to a new llama_kv_cache_dsa_iswa
This commit is contained in:
Xuan-Son Nguyen
2026-08-21 19:52:34 +02:00
committed by GitHub
parent 873e5d8e39
commit 5a32f7b66e
20 changed files with 1412 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-arch.cpp
+5
View File
@@ -110,6 +110,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
{ LLM_ARCH_BAILINGMOE2, "bailingmoe2" },
{ LLM_ARCH_BAILINGMOE3, "bailingmoe3" },
{ LLM_ARCH_DOTS1, "dots1" },
{ LLM_ARCH_DOTS3NOTE, "dots3note" },
{ LLM_ARCH_ARCEE, "arcee" },
{ LLM_ARCH_AFMOE, "afmoe" },
{ LLM_ARCH_LAGUNA, "laguna" },
@@ -273,6 +274,9 @@ static const std::map<llm_kv, const char *> LLM_KV_NAMES = {
{ LLM_KV_ATTENTION_VALUE_LENGTH_MLA, "%s.attention.value_length_mla" },
{ LLM_KV_ATTENTION_KEY_LENGTH_SWA, "%s.attention.key_length_swa" },
{ LLM_KV_ATTENTION_VALUE_LENGTH_SWA, "%s.attention.value_length_swa" },
{ LLM_KV_ATTENTION_KEY_LENGTH_MLA_SWA, "%s.attention.key_length_mla_swa" },
{ LLM_KV_ATTENTION_VALUE_LENGTH_MLA_SWA, "%s.attention.value_length_mla_swa" },
{ LLM_KV_ATTENTION_KV_LORA_RANK_SWA, "%s.attention.kv_lora_rank_swa" },
{ LLM_KV_ATTENTION_INDEXER_HEAD_COUNT, "%s.attention.indexer.head_count" },
{ LLM_KV_ATTENTION_INDEXER_KEY_LENGTH, "%s.attention.indexer.key_length" },
{ LLM_KV_ATTENTION_INDEXER_TOP_K, "%s.attention.indexer.top_k" },
@@ -1056,6 +1060,7 @@ bool llm_arch_supports_sm_tensor(const llm_arch & arch) {
case LLM_ARCH_DEEPSEEK2:
case LLM_ARCH_DEEPSEEK32:
case LLM_ARCH_DEEPSEEK4:
case LLM_ARCH_DOTS3NOTE:
case LLM_ARCH_GLM_DSA:
case LLM_ARCH_BITNET:
case LLM_ARCH_T5: