huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 20:04:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix GQA llama + AWQ

Browse Source
This commit is contained in:
Nicolas Patry 2023-09-26 06:26:23 +00:00
parent c5de7cd886
commit 1ab173a260
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/custom_modeling/flash_llama_modeling.py
View File

@ -179,7 +179,7 @@ def _load_gqa(config, prefix: str, weights):
dim=0,
)
if config.quantize != "gptq":
if config.quantize not in ["gptq", "awq"]:
weight = weight.to(dtype=weights.dtype).to(device=weights.device)
head_size = config.hidden_size // config.num_attention_heads