Comments (3)
Would be nice if someone can tell which version will work
from deepspeedexamples.
Hi @allanj I don't think we have kernel injection support for llama-2 models. If you remove the --use_kernel
flag does the script work?
Additionally, what kind of GPUs are you using? You may be able to utilize DeepSpeed-MII to run the llama-2 model and get significant improvements to inference performance if you have GPUs with compute capability >=8.0:
import mii
client = mii.serve("meta-llama/Llama-2-7b-hf", tensor_parallel=8)
response = client("test prompt")
from deepspeedexamples.
Yes. Removing the --use_kernel
make it work.
Yeah, I realize the DeepSpeed FastGen. Wondering, how does it support the batch size? Or I simply make a for loop about that
from deepspeedexamples.
Related Issues (20)
- 运行e2e_rlhf时报错
- Question: Why did you implemented LoRA on your hand instead of using peft? HOT 1
- [Discussion] Can anyone show the performance on every step with any dataset
- Mistral and Orca Training
- async_pipeline is not exposed in the library HOT 1
- Step3 PPO print error when enable --print_answers HOT 1
- Invalidate trace cache @ step 0: expected module 0, but got module 6
- Step3 hanging for a long time HOT 1
- torch.distributed.DistBackendError: NCCL error in: ../torch/csrc/distributed/c10d/ProcessGroupNCCL.cpp:1333, remote process exited or there was a network error, NCCL version 2.18.6 HOT 3
- running gpt2-xl/test_tune.sh fails - ParquetConfig.__init__() got an unexpected keyword argument 'token'
- Question: Why not padding to the same sequence length within the batch during the sft training phase?
- How to resume Deepspeed-Chat RLHF step-3 training?
- remove redundant code
- The inaccurate flop results after several rounds HOT 1
- Throughput should be `num_queries/latency` as opposed to `num_clients/latency`?
- Codellama finetune
- RLHF problems when using Qwen model HOT 1
- zero3 and enable hybrid engine are not suitable for llama2, how to solve it? HOT 1
- [BUG in Stable Diffusion inference] There's an error on CUDAGraph when using deepspeed inference. How to fix it? HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deepspeedexamples.