Comments (6)
In the fused fast implementations, the inner modules might not be getting called directly. Instead, we use their weights (e.g. backbone.layers.0.mixer.conv1d.weight
) and pass it into a different function (e.g. from the causal-conv1d
package).
from mamba.
I tried setting the fast path variable of the layers to false but I still couldn't get it to work. Is it even possible in the pretained versions?
from mamba.
Is it even possible in the pretained versions?
It should be. Pretrained versions just give a set of weights which are the same no matter the computation path.
I tried setting the fast path variable of the layers to false but I still couldn't get it to work.
You should double check that it's running the path you intend and that the modules are being called directly. For example, you want to hit the following line to call the conv module, instead of using the fast causal_conv1d_fn
. Perhaps it's not hitting this path if you've already pip installed the module because it will automatically use the fast conv1d function.
https://github.com/state-spaces/mamba/blob/main/mamba_ssm/modules/mamba_simple.py#L169
from mamba.
Thank you I hadn't seen that logic there. Because it does not seem feasible to make sure that causal-conv1d is not installed, I will probably have to do some hacky work around to go around that
from mamba.
It should be fairly easy to add another flag to the init function and change the line
if causal_conv1d_fn is None:
to something like
if causal_conv1d_fn is None or not self.use_fast_conv:
from mamba.
Yes, that's what I was thinking
from mamba.
Related Issues (20)
- Question for 'self.use_mem_eff_path and inference_params' HOT 4
- triton.runtime.autotuner.OutOfResources: out of resource: shared memory, Required: 254208, Hardware limit: 101376. HOT 5
- 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 8
- Used selective_scan_cuda and causal_conv1d_cuda, but still very slow to train HOT 1
- mamba / self-attention hybrid generation
- Inference multiple tokens HOT 2
- Error when using FP16 or Mixed precision HOT 3
- How to use Mamba2?
- How to extract whole sentence embeddings HOT 1
- Does mamba support data packing?
- Slow Mamba 2 training speeds with higher d_state values HOT 1
- Where is ‘Block’ class in the new version mamba? HOT 1
- mamba_ssm Install Failure HOT 9
- Sequence parallelism in the mixer (Context Parallelism)
- Support Mamba-codestral
- Why does it take so long to build HOT 1
- Is mamba suitable for time-series classification task? HOT 1
- Question on Comparison between Mamba and S4 HOT 1
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.