@@ -110,6 +110,141 @@ The llama.cpp CANN backend is designed to support Ascend NPU. It utilize the abi
110
110
| vigogne-7b-chat | √ | √ | √ |
111
111
| xverse-7b-chat | √ | √ | √ |
112
112
| Yi-6b-Chat | √ | √ | √ |
113
+ | snowflake-arctic-embed | √ | × | × |
114
+ | all-minilm | √ | × | × |
115
+ | granite-embedding | √ | × | × |
116
+ | smollm | √ | √ | √ |
117
+ | smollm2 | √ | √ | √ |
118
+ | nomic-embed-text | √ | × | × |
119
+ | qwen2 | √ | √ | √ |
120
+ | reader-lm | √ | √ | √ |
121
+ | qwen2.5 | √ | √ | √ |
122
+ | qwen2.5-coder | √ | √ | √ |
123
+ | qwen | √ | √ | √ |
124
+ | paraphrase-multilingual | √ | × | × |
125
+ | tinydolphin | √ | √ | √ |
126
+ | tinyllama | √ | √ | √ |
127
+ | mxbai-embed-large | √ | × | × |
128
+ | bge-large | √ | × | × |
129
+ | starcoder | √ | √ | √ |
130
+ | granite3-moe | √ | √ | √ |
131
+ | llama3 | √ | √ | √ |
132
+ | deepseek-coder | √ | √ | √ |
133
+ | granite3 | √ | √ | √ |
134
+ | moondream | √ | √ | √ |
135
+ | yi-coder | √ | √ | √ |
136
+ | llama-guard3 | √ | √ | √ |
137
+ | qwen2-math | √ | √ | √ |
138
+ | stablelm2 | × | √ | √ |
139
+ | sailor2 | √ | √ | × |
140
+ | gemma3 | √ | √ | × |
141
+ | internlm2 | √ | √ | √ |
142
+ | bge-m3 | √ | × | × |
143
+ | granite3-dense | √ | √ | √ |
144
+ | codegemma | √ | √ | √ |
145
+ | phi | √ | √ | √ |
146
+ | dolphin-phi | × | √ | √ |
147
+ | stable-code | √ | √ | √ |
148
+ | stablelm-zephyr | √ | √ | √ |
149
+ | gemma2 | √ | √ | √ |
150
+ | shieldgemma | × | √ | √ |
151
+ | gemma | √ | √ | √ |
152
+ | starcoder2 | √ | √ | √ |
153
+ | falcon3 | √ | √ | × |
154
+ | deepseek-r1 | √ | √ | × |
155
+ | deepscaler | √ | √ | × |
156
+ | hermes3 | √ | √ | √ |
157
+ | orca-mini | √ | √ | √ |
158
+ | granite-code | √ | √ | √ |
159
+ | opencoder | √ | √ | × |
160
+ | nuextract | √ | √ | √ |
161
+ | phi3 | √ | √ | √ |
162
+ | phi3.5 | √ | √ | √ |
163
+ | nemotron-mini | √ | √ | √ |
164
+ | granite3-guardian | √ | √ | × |
165
+ | exaone3.5 | √ | √ | × |
166
+ | exaone-deep | √ | √ | × |
167
+ | yi | √ | √ | √ |
168
+ | smallthinker | √ | √ | × |
169
+ | yarn-llama2 | √ | √ | √ |
170
+ | xwinlm | √ | √ | √ |
171
+ | wizard-vicuna-uncensored | √ | √ | √ |
172
+ | vicuna | √ | √ | √ |
173
+ | stable-beluga | √ | √ | √ |
174
+ | nous-hermes | √ | √ | √ |
175
+ | medllama2 | √ | √ | √ |
176
+ | llama2-uncensored | √ | √ | √ |
177
+ | meditron | √ | √ | √ |
178
+ | llava | √ | √ | √ |
179
+ | magicoder | √ | √ | √ |
180
+ | wizardlm | √ | √ | √ |
181
+ | wizard-math | √ | √ | √ |
182
+ | wizardcoder | √ | √ | √ |
183
+ | orca2 | √ | √ | √ |
184
+ | codellama | √ | √ | √ |
185
+ | duckdb-nsql | √ | √ | √ |
186
+ | llama2 | √ | √ | √ |
187
+ | deepseek-llm | √ | √ | √ |
188
+ | phi4-mini | √ | √ | × |
189
+ | samantha-mistral | × | √ | √ |
190
+ | yarn-mistral | √ | √ | √ |
191
+ | sqlcoder | √ | √ | √ |
192
+ | neural-chat | √ | √ | √ |
193
+ | bakllava | √ | √ | √ |
194
+ | wizardlm2 | √ | √ | √ |
195
+ | dolphin-mistral | √ | √ | √ |
196
+ | mistral-openorca | √ | √ | √ |
197
+ | openhermes | √ | √ | √ |
198
+ | mistrallite | √ | √ | √ |
199
+ | notus | √ | √ | √ |
200
+ | zephyr | √ | √ | √ |
201
+ | mistral | √ | √ | √ |
202
+ | openchat | √ | √ | √ |
203
+ | mathstral | √ | √ | √ |
204
+ | codeqwen | √ | √ | √ |
205
+ | falcon | √ | √ | √ |
206
+ | dolphincoder | √ | √ | √ |
207
+ | minicpm-v | √ | √ | √ |
208
+ | bespoke-minicheck | √ | √ | √ |
209
+ | llama3-chatqa | √ | √ | √ |
210
+ | llama3-gradient | √ | √ | √ |
211
+ | dolphin-llama3 | √ | √ | √ |
212
+ | llama3-groq-tool-use | × | √ | √ |
213
+ | llama-pro | √ | √ | √ |
214
+ | aya | × | √ | √ |
215
+ | aya-expanse | √ | √ | √ |
216
+ | codegeex4 | × | √ | √ |
217
+ | glm4 | √ | √ | √ |
218
+ | solar | √ | √ | √ |
219
+ | nous-hermes2 | √ | √ | √ |
220
+ | falcon2 | √ | √ | √ |
221
+ | mistral-nemo | √ | √ | √ |
222
+ | llama2-chinese | √ | √ | × |
223
+ | wizard-vicuna | √ | √ | √ |
224
+ | codeup | √ | √ | √ |
225
+ | open-orca-platypus2 | √ | √ | √ |
226
+ | nexusraven | √ | √ | √ |
227
+ | everythinglm | √ | √ | √ |
228
+ | llava-phi3 | √ | × | × |
229
+ | starling-lm | √ | √ | × |
230
+ | olmo2 | √ | √ | × |
231
+ | marco-o1 | × | √ | × |
232
+ | openthinker | √ | √ | × |
233
+ | dolphin3 | √ | √ | × |
234
+ | tulu3 | √ | √ | × |
235
+ | command-r7b | √ | √ | × |
236
+ | command-r7b-arabic | √ | √ | × |
237
+ | deepseek-v2 | × | √ | √ |
238
+ | deepseek-coder-v2 | × | √ | √ |
239
+ | codestral | × | √ | √ |
240
+ | mistral-small | × | √ | √ |
241
+ | wizardlm-uncensored | √ | √ | × |
242
+ | phi4 | × | √ | × |
243
+ | llava-llama3 | √ | × | × |
244
+ | command-r | × | × | √ |
245
+ | phind-codellama | × | × | √ |
246
+ | codebooga | × | × | √ |
247
+ | alfred | × | × | √ |
113
248
114
249
115
250
0 commit comments