huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 03:44:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

add improvements

Browse Source
This commit is contained in:
Mohit Sharma 2025-04-21 15:28:18 +00:00
parent be8e60a918
commit 6ed540b52f
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
server/text_generation_server/models/flash_causal_lm.py
View File

@ -1346,6 +1346,9 @@ class FlashCausalLM(Model):
def batch_type(self) -> Type[FlashCausalLMBatch]: def batch_type(self) -> Type[FlashCausalLMBatch]:
return FlashCausalLMBatch return FlashCausalLMBatch
def get_input_embeddings(self, batch):
batch.inputs_embeds = None
def init_kv_cache( def init_kv_cache(
self, self,
num_blocks: int, num_blocks: int,