Comments (2)
josephrocca
commented on July 18, 2024
CC @JRosenkranz, since you contributed the MLP Speculator feature recently 🙏
from text-generation-inference.
LysandreJik
commented on July 18, 2024
Hey @josephrocca, I don't think directly changing the name of the base model is going to work out here; could you briefly share what you're trying to do here?
If I understand correctly, you're currently using the ibm-fms/llama-13b-accelerator medusa accelerator in FP16 model that's currently based off of the llama-2-13b checkpoint, also in FP16.
You'd like to switch the backend to use a GPT-Q-quantized model for memory constraints I believe? Is it possible for you to quantize it directly using the --quantize command as in the QPTQ docs?
Please share the command here if so and I'll take a look; I'll take a look at the related issue with Command-R plus model as well to see what's happening.
from text-generation-inference.
Related Issues (20)
- Some typo error in the picture of flash_attention.md HOT 1
- Unable to run TGI following the instructions on the readme HOT 5
- docker-compose throws `flash attention is not installed` error HOT 3
- Phi-3-mini-128k crashes on simple query HOT 2
- Add Environment Variable for OTLP Service Name HOT 2
- ImportError: libcuda.so.1: cannot open shared object file: No such file or directory HOT 10
- Tree-attention for medusa HOT 2
- get stucked when run text-generation-benchmark on AMD gpu HOT 2
- Unable to load Qwen2-72B-Instruct-exl2 model HOT 2
- `mistralai/Mixtral-8x22B-Instruct-v0.1`: Getting `RuntimeError: 'ptxas' failed with error code 127` while warming up on 8 GPUs HOT 2
- `mistralai/Mixtral-8x22B-Instruct-v0.1`: Successful warmup, crashes on inference HOT 2
- Long install report HOT 1
- P40 with USE_FLASH_ATTENTION=False HOT 2
- Sparse Marlin HOT 3
- protobuf version not compatible HOT 1
- Qwen/Qwen2-72B-Instruct-AWQ gibberish output in 2.0.4 HOT 3
- Will Support Disaggregating Prefill and Decoding? HOT 1
- `top_p` messes up `top_logprobs` HOT 2
- template_error in /chat/completions HOT 2
- how to launch a service using downloaded model weights? 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 text-generation-inference.