Comments (2)
Hey @hustxiayang, IIRC, applying the tree-attention results in significantly more compute than using argmax, so the throughput cost is too high to justify the value.
Don't quote me on this but IIRC without the tree the speedup is 2x, while with the tree there is a maximum of ~3x speedup but throughput significantly decreases (divided by 10-20x).
To confirm with @Narsil eventually, hope it sheds some light on the question in the meantime.
from text-generation-inference.
Hi, I suppose you observe speedups from one of:
text-generation-inference/gemma-7b-it-medusa
text-generation-inference/Mixtral-8x7B-Instruct-v0.1-medusa
text-generation-inference/Mistral-7B-Instruct-v0.2-medusa
If that is the case, which dataset(s) did you use?
Another question: do you plan to support typical sampling mentioned in their paper?
from text-generation-inference.
Related Issues (20)
- AttributeError: 'MixtralLayer' object has no attribute 'mlp' HOT 3
- Error loading Qwen2-72B-Instruct with EETQ HOT 1
- [RFC]Add Auto-Round Support HOT 18
- OpenAI-compatible API has a discrepancy with original OpenAI API when using tool calls HOT 2
- Error with sharded Mixtral HOT 5
- Unable to load the local model file into LoRA adaptors HOT 10
- Could not import Flash Attention enabled models: cannot import name 'FastLayerNorm' HOT 1
- Error "EOF while parsing an object..." with tool_calls HOT 1
- DeepSeek Coder V2: sharded is not supported for AutoModel HOT 2
- loading fast tokenizer implementation for cached model with `HF_HUB_OFFLINE=1` fails HOT 2
- Can tgi surpport non tokenizer model? HOT 1
- Unknown variant Qwen2
- Enable torch.float8_e5m2 for Ada lovelace HOT 1
- Errors when serving Taiwan LLama3 model HOT 2
- Understanding how max-batch-prefill-tokens works
- Gemma2 fails due to missing model.embed_tokens.weight
- Error when running on Idefics-2 with expanded vocabulary
- Phi-3's new rope scaling type `longrope` not supported HOT 3
- Is there any possibility to support `Phi-3-vision-128k-instruct`? HOT 1
- Question about the multi-Lora feature 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 text-generation-inference.