Comments (13)
I found a workaround, at least for T4. Set the model to half-precision to avoid this error:
model = MambaLMHeadModel.from_pretrained('state-spaces/mamba2-130m')
model = model.half()
Let me know if you understand why this works :)
from mamba.
Looks like a Triton error, which GPU do you use?
from mamba.
rtx2080ti with driver version 535.171.04 right now, i am trying to use different version of python or newest trition 2.3.1 or pytorch
to fix this problem
from mamba.
I'm not sure triton supports GPUs before Ampere (e.g. 2080) very well
from mamba.
I just borrowed a rtx3060 (driver version 535.171.04) to test the code and it works. and triton version is 2.3.1. thanks
from mamba.
same issue here but using V100 :(
from mamba.
With newest triton version (2.3.1), this seems mainly related to the used GPU. I also ran into this error on an RTX 2080 Ti, thus I tried to reproduce the error on different GPUs I have available.
Setup: Nvidia driver 535.161.07, Cuda 11.8, Triton 2.3.1, mamba-ssm v2.0.3
Working GPUs: V100, RTX 3090, RTX 4090, A100 (40GB & 80GB)
Index Error (map::at): RTX 2080 Ti, Titan RTX, Quadro RTX 6000
--> it seems the error only occurs for the Turing microarchitecture
@ghaddarAbs V100 works for me; maybe update triton to 2.3.1?
from mamba.
@jsie7 thanks for suggesting I will try it out ... which torch version you used ?
from mamba.
@jsie7 thanks for suggesting I will try it out ... which torch version you used ?
I'm using v2.0.1
from mamba.
I experienced same problem :(
Driver Version: 550.54.14
CUDA Version: 12.4 # by nvcc -V
Tesla T4
triton==2.3.1
I only installed torch with cuda12.1 support.
from mamba.
I experienced same problem :(
Driver Version: 550.54.14 CUDA Version: 12.4 # by nvcc -V Tesla T4 triton==2.3.1
I only installed torch with cuda12.1 support.
The Tesla T4 is also based on the Turing microarchitecture. This just further confirms that it's an issue with that architecture.
from mamba.
Thanks @maksymdolgikh this worked for me, also no idea why this works though.
from mamba.
I found a workaround, at least for T4. Set the model to half-precision to avoid this error:
model = MambaLMHeadModel.from_pretrained('state-spaces/mamba2-130m') model = model.half()
Let me know if you understand why this works :)
worked on 2080Ti for me too.
from mamba.
Related Issues (20)
- Questions about Chunk_size using Triton optimization in SSD kernel HOT 2
- When I run mamba2 : ImportError: libcudart.so.11.0: cannot open shared object file: No such file or directory
- Possible bug when running evaluation with self.use_mem_eff_path=False
- Typo of dconv at Line 231 of modules/mamba2.py HOT 1
- How to load mamba1's weight to mamba2 ? HOT 1
- Small datasets HOT 4
- Help with _chunk_state_fwd. HOT 1
- Assertion error in ssd_minimal HOT 5
- Questions regarding pretrained Mamba2-Attention Hybrid Model HOT 2
- (about the paper) In the Section5.1, I have a question: Why M matrix, whose element is also matrix, can finally be (T, T) size? HOT 2
- A mamba scaling problem given the perplexity score curves shown in the TTT paper HOT 2
- Passing an initial_conv_state in mamba_split_conv1d_scan_combined? HOT 2
- Self-distillation technique
- Question for 'self.use_mem_eff_path and inference_params'
- triton.runtime.autotuner.OutOfResources: out of resource: shared memory, Required: 254208, Hardware limit: 101376. HOT 2
- I want to ask does anyone know how to solve this problem
- /anaconda3/lib/python3.11/site-packages/causal_conv1d_cuda.cpython-311-x86_64-linux-gnu.so: undefined symbol: _ZN3c107WarningC1ENS_7variantIJNS0_11UserWarningENS0_18DeprecationWarningEEEERKNS_14SourceLocationENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEEb HOT 1
- Mamba-2 Error: `'NoneType' object has no attribute 'causal_conv1d_fwd'` HOT 2
- Used selective_scan_cuda and causal_conv1d_cuda, but still very slow to train
- mamba / self-attention hybrid generation
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 mamba.