Comments (8)
The GPUs shouldn't be an issue really. I'll try it out on the same hardware and get back to you with results. Can you make a new conda env and try again in the meantime?
I already tried it two times as I was also setting up something else in the background the first time around, but both resulted in the same error.
I just rented 2x 3090s on runpod and received the exact same error (it works on 8x and 4x A40s so multi-GPU isn't an issue). I'll run some more tests to see what's wrong, will keep you updated if I find out what the problem is.
from aphrodite-engine.
Hi. What's your hardware? Also please describe how to reproduce the error, e.g. did you run Aphrodite through a conda env?
from aphrodite-engine.
Yes I run it through conda env, basically just like the installation instructions say.
As soon as I try to start the server, no matter which arguments, it spits out the error.
As for the hardware:
OS: Ubuntu desktop 22.04 lts
CPU: 8700k
32 GB Ram, Samsung SSD
So rather normal so far, but:
2x 3090 as the GPU
I could retry it later with just a single GPU plugged in.
from aphrodite-engine.
Yes I run it through conda env, basically just like the installation instructions say. As soon as I try to start the server, no matter which arguments, it spits out the error.
As for the hardware: OS: Ubuntu desktop 22.04 lts CPU: 8700k 32 GB Ram, Samsung SSD So rather normal so far, but: 2x 3090 as the GPU
I could retry it later with just a single GPU plugged in.
The GPUs shouldn't be an issue really. I'll try it out on the same hardware and get back to you with results. Can you make a new conda env and try again in the meantime?
from aphrodite-engine.
The GPUs shouldn't be an issue really. I'll try it out on the same hardware and get back to you with results. Can you make a new conda env and try again in the meantime?
I already tried it two times as I was also setting up something else in the background the first time around, but both resulted in the same error.
from aphrodite-engine.
Maybe this here helps:
ray-project/ray#25952
As it calls .fs of pyarrow, so maybe install it to double-check?
It might do some fancy import magic which is why it isn't thrown earlier, but I'm only guessing.
Can try it myself later in the day...
Relevant part of the code in ray
from aphrodite-engine.
Maybe this here helps: ray-project/ray#25952
As it calls .fs of pyarrow, so maybe install it to double-check? It might do some fancy import magic which is why it isn't thrown earlier, but I'm only guessing. Can try it myself later in the day...
Can confirm that pip install pyarrow
solves this. Thanks for pointing that out!
from aphrodite-engine.
Latest commit 592ee204a658f82f1467d76e25d185054f1e27f0 should solve this. Marking this issue as complete.
from aphrodite-engine.
Related Issues (20)
- [New Model]: Phi3ForCausalLM
- [Bug]: Fails to start with error UnicodeDecodeError: 'utf-8' codec can't decode byte 0xf8 in position 0: invalid start byte HOT 2
- [Bug]: Cannot load Mixtral GGUF model? HOT 13
- [Installation]: Docker runs out of CPU swap size on 8 GPUs. How to lower swap_space to be less than 4GB per GPU? HOT 1
- [Bug]: Moe's no longer working HOT 3
- [Bug]: [rank0]: KeyError: 'input_ids' HOT 2
- [Usage]: Higher Context Length. HOT 2
- [Feature]: WARNING: Model is quantized. Forcing float16 datatype HOT 4
- [Misc]: INT8 kv quant seems removed.
- [Bug]: unable use all the vram in wsl cuda environment
- [Bug]: /metrics Endpoint Returns 404
- [Feature]: An alternative to `max_tokens` which defaults to `minimum(max_tokens, remaining_tokens)`
- [Bug]: SnowStorm-v1.15-4x8B: Watchdog caught collective operation timeout: WorkNCCL(SeqNum=1, OpType=BROADCAST, NumelIn=128, NumelOut=128, Timeout(ms)=600000)
- [Usage]: OOM crash following Offline Inference setup HOT 3
- [Feature]: Speculative decoding with dual GPUs
- [Bug]: Segmentation fault (core dumped)
- [Bug]: Docker container refuses connection (read ECONNRESET)
- [Installation]: pip installs no executable HOT 3
- [Feature]: Suggestion for build older versions of aphrodite engine's docker images
- [Bug]: Cannot start GGUF FP16 models
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.