Comments (4)
Thanks for the request. As we discussed in private, mirostat support is on the way. After that, we'll focus on a few more deterministic samplers then we can finally move to CFG and grammars.
I have not experimented with exllamav2 kernels yet, but I will assume it'll be straightforward enough to migrate from v1 to v2.
from aphrodite-engine.
At the moment, we've added support for:
- mirostat
- exllamav2 (though not the variable bitrates, GPTQ only)
CFG support is not planned and will likely not happen in the foreseeable future, as it slows down generations.
from aphrodite-engine.
Re-opening this issue so we can keep track of CFG support. After discussing internally, we decided to add it (but not as a high priority addition). We'll likely need to separate CFG requests to their own unique batches, so the throughput cost doesn't affect regular requests.
from aphrodite-engine.
Just saying that as an individual user, having CFG support with 8 bit KV cache is, obviously, really useful. exl2 does this too and it's killer. The net gain for quality feels like it's cheating.
I wonder if there'd be room to further squeeze the second cache - given that it's useful even when you just pass an empty string (or <s>) as the prompt?
I don't suppose the maths of CFG still makes sense with a shorter negative context? ...maybe just kludge it with
"I pinky promise that we found a sink token and not a null reference down there in the context mr transformer don't worry about it just keep up that forward() okay buddy!"
I feel it might not even be a bad thing if the negative guidance was, yknow, low quality? It's gotta stay on topic but
/shrug
Not like I'd know. So I'm greatful that you guys do. Keep it up and thanks for your work.
from aphrodite-engine.
Related Issues (20)
- [Installation]: install fails on Ubuntu 24.04 HOT 2
- [Bug]: New Numpy version breaks installation HOT 2
- [Misc]: Is there a way to log the prompts content request in the console? HOT 2
- [Usage]: native nvlink support or not agnostic to mobo
- [Usage]: So can AMD NAVI GPUs be used with aphrodite? Which GPUs? HOT 1
- [Usage]: How to use prefix caching? HOT 3
- [Bug]: (exl2) First request with guided_json/guided_regex param creates crash loop for 10 minutes HOT 1
- [Bug]: torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 448.00 MiB. GPU HOT 11
- [Bug]: Using SillyTavern slow down aphrodite generation speed. HOT 2
- [Installation]: Could not build wheels for aphrodite-engine, xformers
- Support 3bit quip# model.
- [Bug]: LLMs have difficulties generating new line characters "\n", which is extremely obvious while generating code blocks in markdown
- [Feature] GGUF memory usage optimization HOT 1
- [Usage]: Set memory usuage for each gpu seperately HOT 1
- [Usage]: Only One GPU Being Used HOT 2
- [Usage]: Low Throughput HOT 2
- [Bug]: CUDA out of memory for Dracones/c4ai-command-r-plus_exl2_5.5bpw with 192GB VRAM - 4*RTX 6000 Ada HOT 1
- [Bug]: Issue when loading Mistral-Nemo-Instruct-2407-Q5_K_M HOT 4
- [Bug]: Llama 3.1 outputs gibberish when --kv-cache-dtype fp8 but AWQ model works fine HOT 4
- [Bug]: CMake build fails for rc_054: CUDA 20 dialect not supported by NVIDIA compiler for multiple targets HOT 3
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.