huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-12 04:44:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Just medusa values now.

Browse Source
This commit is contained in:
Nicolas Patry 2024-08-13 13:02:48 +02:00
parent 549f0e9ca7
commit 4c8dcbb76d
No known key found for this signature in database
GPG Key ID: 64AF4752B2967863
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/flash_causal_lm.py
View File

@ -1507,7 +1507,7 @@ class FlashCausalLM(Model):
input_lengths_tensor=cuda_graph["input_lengths"], input_lengths_tensor=cuda_graph["input_lengths"],
prefix_lens=batch.prefix_lens, prefix_lens=batch.prefix_lens,
prefix_lens_tensor=prefix_lens_tensor, prefix_lens_tensor=prefix_lens_tensor,
state=cuda_graph["state"], state=cuda_graph.get("state"),
): ):
# Replay the graph # Replay the graph
cuda_graph["graph"].replay() cuda_graph["graph"].replay()