Comments (1)
Narsil
commented on May 25, 2024
We're not interested in supporting PP at all.
This project is interested in making good LATENCY, we're barely interested in throughput (it comes for free so we take it, but it's really not the focus of this project).
If you there's an argument for making PP good for LATENCY we'll be taking it, but we've never seen anything like it, the issue being having differently sized chunks of work on difference GPUs.
Synchronization while slow, is still much more efficient for the overall pipeline.
Other projects will be better suited for throughput most likely.
Inter node is never going to be worth it compared to quantization currently.
from text-generation-inference.
Related Issues (20)
- Add `grammar` to chat/completions endpoint / Messages API
- Add Intel Arc iGPU support (Meteor Lake)
- TGI-2.0.2 encounter "CUDA is not available"
- Encounter install error when install vllm package.
- Mistral7b takes 4 times its size in VRAM on A100 HOT 5
- Regarding llama3-70b-instruct
- Use pre-built FA2, vllm, quantization kernels in the dockerfiles
- "docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data -e HUGGING_FACE_HUB_TOKEN={your_token} ghcr.io/huggingface/text-generation-inference:latest --model-id $model --num-shard $num_shard" showing error with my token id that "Unable to find image 'ghcr.io/huggingface/text-generation-inference:latest' locally latest: Pulling from huggingface/text-generation-inference docker: no matching manifest for linux/arm64/v8 in the manifest list entries. See 'docker run --help'."
- Cannot use Inference Endpoint: UnprocessableEntityError: Error code: 422 - {'error': 'Template error: template not found', 'error_type': 'template_error'} HOT 1
- llama3-70B-Instruct-AWQ causing CUDA error: an illegal memory access was encountered
- how do I adjust the logging level when launching via the docker container?
- [Question] Onnx support in TGI
- Automatic NUMA binding
- How to share memory among 2 GPUS for distributed inference? HOT 10
- text generation details not working when stream=False HOT 1
- concurrent requests permit limit is broken
- Multi-Model Endpoint support in Sagemaker
- Logging has no formating when using docker enviroment instead of command
- SnapKV support
- Question about KV cache HOT 3
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 text-generation-inference.