Skip to content

GitLab

Commit 85def94c authored by zhuwenwen's avatar zhuwenwen
Browse files

update llama.py

parent 1e4ba896
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 0 deletions
vllm/model_executor/models/llama.py
View file @ 85def94c
...@@ -455,6 +455,7 @@ class LlamaForCausalLM(nn.Module, SupportsLoRA): ...@@ -455,6 +455,7 @@ class LlamaForCausalLM(nn.Module, SupportsLoRA):
self.quant_config=quant_config self.quant_config=quant_config
self.use_llama_nn = os.environ.get('LLAMA_NN') == '1' self.use_llama_nn = os.environ.get('LLAMA_NN') == '1'
self.use_lm_nn = os.environ.get('LM_NN') == '1'
self.use_gemm_pad = os.environ.get('GEMM_PAD') == '1' self.use_gemm_pad = os.environ.get('GEMM_PAD') == '1'
self.use_fa_pad = os.environ.get('FA_PAD') == '1' self.use_fa_pad = os.environ.get('FA_PAD') == '1'
self.use_awq_pad = os.environ.get('AWQ_PAD') == '1' self.use_awq_pad = os.environ.get('AWQ_PAD') == '1'
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment