huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-28 05:22:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix

Browse Source
This commit is contained in:
OlivierDehaene 2024-06-05 21:32:46 +02:00
parent 35f27cbcc1
commit 51fa606875
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
server/text_generation_server/models/vlm_causal_lm.py
View File

@ -230,7 +230,7 @@ class VlmCausalLM(BaseFlashMistral):
cu_seqlen_prefill = batch.cu_seqlen_prefill cu_seqlen_prefill = batch.cu_seqlen_prefill
kv_cache = self.kv_cache kv_cache = self.kv_cache
block_tables = batch.block_tables_tensor block_tables = batch.block_tables_tensor
slots = batch.slots_tensor[batch.slot_indices] slots = batch.slots[batch.slot_indices]
input_lengths = batch.input_lengths_tensor input_lengths = batch.input_lengths_tensor
max_s = batch.max_seqlen max_s = batch.max_seqlen
lm_head_indices = batch.prefill_head_indices lm_head_indices = batch.prefill_head_indices
@ -269,7 +269,7 @@ class VlmCausalLM(BaseFlashMistral):
cu_seqlen_prefill = batch.cu_seqlen_prefill cu_seqlen_prefill = batch.cu_seqlen_prefill
kv_cache = self.kv_cache kv_cache = self.kv_cache
block_tables = batch.block_tables_tensor block_tables = batch.block_tables_tensor
slots = batch.slots_tensor[batch.slot_indices] slots = batch.slots[batch.slot_indices]
input_lengths = batch.input_lengths_tensor input_lengths = batch.input_lengths_tensor
max_s = batch.max_seqlen max_s = batch.max_seqlen
lm_head_indices = batch.prefill_head_indices lm_head_indices = batch.prefill_head_indices