[Fix] Reduce memory usage for loading llava model & Remove EntryClassRemapping (#1308)

This commit is contained in:
Lianmin Zheng
2024-09-02 21:44:45 -07:00
committed by GitHub
parent a5a134f39f
commit f64eae3a29
17 changed files with 105 additions and 158 deletions
+2 -3
View File
@@ -15,12 +15,11 @@ limitations under the License.
"""Inference-only Mistral model."""
from sglang.srt.models.llama2 import LlamaForCausalLM
from sglang.srt.models.llama import LlamaForCausalLM
class MistralForCausalLM(LlamaForCausalLM):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
pass
EntryClass = MistralForCausalLM