github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-28 21:17:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

[inference]Optimize the usage of the mid tensors space in flash attn (#5304)

Browse Source 
* opt flash attn

* opt tmp tensor

* fix benchmark_llama

* fix code style

* fix None logic for output tensor

* fix adapted to get_xine_cache

* add comment

* fix ci bugs

* fix some codes

* rm duplicated codes

* rm duplicated codes

* fix code style

* add _get_dtype in config.py
This commit is contained in:
yuehuayingxueluo
2024-01-26 14:00:10 +08:00
committed by GitHub
parent af8359c430
commit 4f28cb43c0
16 changed files with 199 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/inference/benchmark_llama.py
View File

@@ -91,7 +91,7 @@ def benchmark_inference(args):
config.pad_token_id = config.eos_token_id
model = transformers.LlamaForCausalLM(config).cuda()
model = model.eval()
tokenizer = AutoTokenizer.from_pretrained("/home/caidi/llama_model/")
tokenizer = AutoTokenizer.from_pretrained("hf-internal-testing/llama-tokenizer")
if args.dtype == "fp16":
model = model.half()