Comments (5)
A 2.4-3.4x speedup, while impressive, cannot be judged in a vacuum. You always need to consider the tradeoffs between speed, quality, and memory use. The difference in memory use should be negligible. However, since you need to specifically finetune the model in order to enable this speedup this degrades the quality of the outputs. The paper reports an increase in perplexity from 8.0 to 9.5. These values are not directly comparable to llama.cpp values since they depend on a lot of factors but I think that this is a lot more than I would intuitively expect from e.g. quantization.
My personal philosophy is that I want to enable the evaluation of large models with negligible precision loss compared to the original weights at the lowest possible cost. So I personally am not interested in implementing something like this.
from llama.cpp.
To clarify my position: I am not willing to do an implementation myself but I would be willing to review someone else's implementation.
from llama.cpp.
My read is the change is to training not code. So it's a fine tuning procedure on the model itself? Is that right or am I missing something?
from llama.cpp.
llama.cpp would still need code changes specifically to support the technique described in the paper.
from llama.cpp.
I'll poke my head over there and see if they're willing to help with that because I'd be very interested in running this. Even with somewhat lower accuracy because I get billed by the millisecond for inference so anything that can speed it up would be a huge savings.
from llama.cpp.
Related Issues (20)
- Feature Request: Prevent server.exe from being detected as ? Trojan:Win32/Wacatac.B!ml
- Bug: convert-hf-to-gguf-update.py breaks in Windows Python 3.11.5 HOT 10
- Bug: Could NOT find BLAS (missing: BLAS_LIBRARIES) HOT 2
- Bug: Phi-3 4K output broken after 2000~ tokens (Reproducible) HOT 9
- Bug: test run on stories15M-q4_0.gguf result in Segmentation fault. HOT 3
- GGUF models inference speed - Why is GGUF model inference fast on my Mac but slow on cluster?
- [SYCL] Bug: check_allow_gpu_index error: device_index:0 is out of range: [0--2] HOT 1
- Bug: STATIC COMPILE not static anymore :( HOT 2
- Bug: Grammar readme seems incorrect HOT 2
- Bug: GGUF of Llama 3 8B appears to use smaug-bpe pretokenizer? HOT 2
- llama : support Mamba-2
- llama_model_load: error loading model: check_tensor_dims: tensor 'token_embd.weight' not found HOT 1
- Bug: gpu hang after bde7cd3cd949c1a85d3a199498ac98e78039d46f HOT 4
- Bug: Docker containers failing (libgomp.so.1) HOT 7
- Bug: Does any convert.py supprt llama3? HOT 7
- Bug: prefix completion endpoint with /v1 HOT 2
- Bug: self-extend does not seem to work with granite code instruct models (server/main)
- Bug: failed compile rocm build on windows using cmake HOT 7
- Feature Request: tokenized history HOT 1
- Feature Request: Support for NVEmbed 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 llama.cpp.