Comments (8)
StefanGliga
commented on June 5, 2024
1
Could it be that GQA+AWQ+NTK RoPE scaling all together are somehow conflicting?
from aphrodite-engine.
AlpinDale
commented on June 5, 2024
Try reducing the --max-num-batched-tokens and try again.
from aphrodite-engine.
g4rg
commented on June 5, 2024
Same thing with --max-num-batched-tokens 8192.
This is on A100 80GB.
from aphrodite-engine.
AlpinDale
commented on June 5, 2024
I'm getting the same error with 34B-AWQ. Looks like AWQ kernels don't support CodeLlama properly? Investigating now.
from aphrodite-engine.
AlpinDale
commented on June 5, 2024
Seems like it. GPTQ kernels behave as normal though. I'll try without the RoPE scaling with 34B in a bit.
from aphrodite-engine.
g4rg
commented on June 5, 2024
34B fp16 + RoPE works
from aphrodite-engine.
AlpinDale
commented on June 5, 2024
Sorry I forgot about this issue. It should be fixed by now. Have you run into any problems with 70B AWQ + RoPE lately? @g4rg
from aphrodite-engine.
g4rg
commented on June 5, 2024
Yes, it has been working for a while now. Sorry, forgot to update.
from aphrodite-engine.
Related Issues (20)
- [Bug]: HOT 1
- [Usage]: Please provide the environment variable that closes the KoboldAI Lite page.
- [Performance]: Memory Usage Fix for gguf. HOT 3
- [Installation]: ValueError: 17 is not a valid GGMLQuantizationType HOT 21
- [Installation]: Upload Aphrodite v0.5.2 On Pypi.org HOT 3
- [Usage]: What to set to get acceptable performance on Pascal GPUs? (Non-P100) HOT 2
- [Installation]: Installing from source does not work. undefined symbol: _ZN3c104cuda14ExchangeDeviceEa HOT 8
- [Bug]: PermissionError: [Errno 13] Permission denied: '/app/aphrodite-engine/.triton' HOT 3
- [Bug]: LoRA broken when TP>1
- [Bug]: LoRA fails to load HOT 1
- [Feature]: Exllamav2 Q4 cache HOT 2
- [Usage]: Lora Adapter Parameter while inferencing HOT 1
- [Bug]: Flash attention cannot be used on v0.5.3 HOT 7
- [Bug]: GPUExecutor throwing 'TypeError: 'type' object is not subscriptable' on 0.5.3 HOT 2
- [Bug]: Cannot load 70b exl2 5bpw model across 4 GPUs. HOT 10
- [Bug]: torch._dynamo.exc.BackendCompilerFailed with command-r-plus HOT 3
- [Bug]: Cannot load llama-3 gguf based models HOT 1
- [Bug]: Int8 k/v cache calibrate don't work with QWen model?
- [Feature]: request for support DeepseekV2ForCausalLM.
- [Bug]: Running aphrodite throws ImportError 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 aphrodite-engine.