Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix(server): fix cohere (#2249)

This commit is contained in:
OlivierDehaene 2024-07-18 14:00:13 +00:00 committed by GitHub
parent da82c63a4f
commit 1d1b1efa01
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/text_generation_server/models/custom_modeling/flash_cohere_modeling.py
View File

@ -259,8 +259,8 @@ class FlashCohereAttention(torch.nn.Module):
cu_seqlen_prefill, cu_seqlen_prefill,
kv_cache, kv_cache,
block_tables, block_tables,
input_lengths,
slots, slots,
input_lengths,
max_s, max_s,
): ):
qkv = self.query_key_value(hidden_states) qkv = self.query_key_value(hidden_states)