|
152 | 152 | BACKEND_LIST = ['turbomind', 'pytorch'] |
153 | 153 |
|
154 | 154 | RESTFUL_MODEL_LIST = [ |
155 | | - 'Qwen/Qwen3-0.6B', 'Qwen/Qwen3-VL-2B-Instruct', 'Qwen/Qwen3-30B-A3B', 'internlm/Intern-S1', |
156 | | - 'internlm/internlm2_5-20b', 'Qwen/Qwen3-32B', 'OpenGVLab/InternVL3_5-30B-A3B', 'OpenGVLab/InternVL3-38B', |
157 | | - 'Qwen/Qwen3-VL-8B-Instruct', 'internlm/internlm3-8b-instruct', 'meta-llama/Llama-3.2-3B-Instruct', |
| 155 | + 'Qwen/Qwen3.5-27B', 'Qwen/Qwen3.5-35B-A3B', 'Qwen/Qwen3-0.6B', 'Qwen/Qwen3-VL-2B-Instruct', |
| 156 | + 'Qwen/Qwen3-30B-A3B', 'internlm/Intern-S1', 'internlm/internlm2_5-20b', 'Qwen/Qwen3-32B', |
| 157 | + 'OpenGVLab/InternVL3_5-30B-A3B', 'OpenGVLab/InternVL3-38B', 'Qwen/Qwen3-VL-8B-Instruct', |
| 158 | + 'internlm/internlm3-8b-instruct', 'meta-llama/Llama-3.2-3B-Instruct', |
158 | 159 | 'Qwen/Qwen3-VL-30B-A3B-Instruct' |
159 | 160 | ] |
160 | 161 |
|
161 | 162 | RESTFUL_BASE_MODEL_LIST = [ |
162 | | - 'Qwen/Qwen3-8B-Base', 'internlm/internlm2_5-20b', 'Qwen/Qwen3-4B', 'internlm/internlm3-8b-instruct' |
| 163 | + 'Qwen/Qwen3.5-2B-Base', 'Qwen/Qwen3.5-35B-A3B-Base','Qwen/Qwen3-8B-Base', |
| 164 | + 'internlm/internlm2_5-20b', 'Qwen/Qwen3-4B', 'internlm/internlm3-8b-instruct' |
163 | 165 | ] |
164 | 166 |
|
165 | 167 | SUFFIX_INNER_AWQ = '-inner-4bits' |
|
0 commit comments