Comments (2)
我看了 LLaMa / Baichuan 都是在用 sample。 是否支持,还看 LLM 本身默认配置是否开启 beam search,现在还没看到哪个在用。
如果你发现哪个模型默认用了,请告诉我们。
from lmdeploy.
Close it since no more activity over two weeks. Feel free to reopen it if it is still an issue
from lmdeploy.
Related Issues (20)
- [Feature] TurboMind support W8A8 or FP8 KV Cache HOT 7
- 可以支持一下:InternLM-XComposer2 模型吗? HOT 2
- [Feature] random_seed参数
- [Feature] TurboMind support Baichuan 13b and Baichuan2 13b HOT 6
- RelayAttention discussion HOT 2
- [Docs] 0.4.0版本更新好了吗 HOT 3
- [Docs] 请问当前lmdeploy支持大模型的工具调用能力吗? HOT 1
- [Feature] 多模态模型量化示例 HOT 1
- [Bug] DeprecationWarning: concurrency_count has been deprecated. Set the concurrency_limit directly on event listeners e.g. btn.click(fn, ..., concurrency_limit=10) or gr.Interface(concurrency_limit=10). If necessary, the total number of workers can be configured via `max_threads` in launch(). HOT 2
- [Bug] 更新0.4.0版本后,qwen1.5运行报错 HOT 7
- [Feature] Support QuaRot quantization scheme HOT 1
- [Bug] Cannot chat with converted model of Qwen1.5 awq model. HOT 1
- [Docs] Compared with vllm, lmdeploy has less throughput. Is there any config wrong? HOT 8
- [Feature] Support for OpenGVLab/InternVL-Chat-V1-2-Plus HOT 14
- [Bug] qwen1.5-32b-chat HOT 13
- [Feature] Support Quantized InternLM-XComposer2-VL model
- [Feature] InternVL-Chat-V1.5 Support HOT 6
- logger in `lmdeploy/serve/async_engine.py` is hard coded HOT 1
- calibration dataset in AWQ support customization
- [Bug] sometimes Internal Server Error 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 lmdeploy.