xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-09 15:57:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add comment

Browse Source
This commit is contained in:
Woosuk Kwon 2024-04-26 05:27:27 +00:00
parent aa092834bb
commit d16a348477
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/model_executor/models/jax/gemma.py
View File

@ -154,6 +154,7 @@ class Attention(nn.Module):
# Write the incoming keys and values to KV cache. # Write the incoming keys and values to KV cache.
k_cache, v_cache = cache k_cache, v_cache = cache
# FIXME(woosuk): Uncomment this.
# k_cache, v_cache = write_to_kv_cache( # k_cache, v_cache = write_to_kv_cache(
# key_proj, value_proj, k_cache, v_cache, slot_mapping) # key_proj, value_proj, k_cache, v_cache, slot_mapping)