huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-19 22:02:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge fd92054e1d into 4645678ff0

Browse Source
This commit is contained in:
Curtis Ruck 2025-04-16 17:11:23 +09:00 committed by GitHub
commit a7aff220e0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
server/text_generation_server/layers/attention/flashinfer.py
View File

@ -84,16 +84,16 @@ def use_prefill_with_paged_kv_state(
token = prefill_with_paged_kv_state.set(state)
try:
state.plan(
qo_indptr=cu_seqlens,
paged_kv_indptr=indptr,
paged_kv_indices=block_tables,
paged_kv_last_page_len=last_page_len,
num_qo_heads=num_heads,
num_kv_heads=num_kv_heads,
head_dim=head_size,
kv_data_type=kv_dtype,
cu_seqlens,
indptr,
block_tables,
last_page_len,
num_heads,
num_kv_heads,
head_size,
page_size,
q_data_type=q_dtype,
page_size=page_size,
kv_data_type=kv_dtype,
)
yield
finally: