huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 12:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Adding assertion.

Browse Source
This commit is contained in:
Nicolas Patry 2024-12-02 19:40:57 +01:00
parent b4c5ca5a58
commit 45eb84e4b6
No known key found for this signature in database
GPG Key ID: D2920555C90F704C
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -1416,6 +1416,10 @@ class FlashCausalLM(Model):
max_current_length=max_s,
)
else:
if bs > max_bs:
raise RuntimeError(
"Cuda graphs should be generated in decreasing order size to reduce VRAM usage"
)
input_ids = self.cuda_graphs[max_bs]["input_ids"][:bs]
position_ids = self.cuda_graphs[max_bs]["position_ids"][:bs]
if ATTENTION == "flashinfer":