Comments (6)
aarnphm
commented on May 29, 2024
I think t4 is too old for mistral 😄
I haven't tested extensively on T4 yet. But Mistral has been tested with a10g, L4, a100.
from openllm.
sankethgadadinni
commented on May 29, 2024
@aarnphm I think with dtype float16 it should work.
What about LLama?
from openllm.
aarnphm
commented on May 29, 2024
llama should work.
from openllm.
aarnphm
commented on May 29, 2024
btw float16 is default.
from openllm.
sankethgadadinni
commented on May 29, 2024
@aarnphm No even LLama isn't working.
bfloat16 is default.
from openllm.
aarnphm
commented on May 29, 2024
I think t4 is too old now. 😄
from openllm.
Related Issues (20)
- bug: AttributeError in Phi-2 Model Initialization Using BentoML OpenLLM Docker Container HOT 4
- bug: Docker images with GPTQ quantized models do not have auto-gptq or optimum installed HOT 1
- How to run a docker image on multiple GPUs?
- bug: TypeError attribute name must be string, not 'NoneType' HOT 3
- feat: add vllm 0.3.0 support HOT 3
- bug: running any model results on the error: "Error: [bentoml-cli] `serve` failed: Invalid Tag _service:svc"
- bug: Can't load local models with (No such file or directory) error
- How to update the prompt template without change openllm-core config
- feat: Document usage of request_id
- Can't pass workers_per_resource to the bentoml container HOT 2
- RunnerService: MAX_MODEL_LEN is not reflected to the llm._max_model_len HOT 2
- bug: Requests with "use_beam_search: true" fail with an unclear exception message.
- bug: Error in sending post request for bentoml container service HOT 1
- Runtime error about concurrency
- When attempting to add the CohereForAI/aya-101 model using CohereForAI's Aya model, an error occurred during the loading process.
- openllm_core.exceptions.OpenLLMException: Failed to initialise vLLMEngine due to the following error: Model architectures ['T5ForConditionalGeneration'] are not supported for now. HOT 1
- bug: not generate eos_token when using qwen7B-chat
- bug: start chatglm-6b locally err
- I'm having trouble getting statted with openllm, but I don't want to use conda and I have WSL2 HOT 1
- feat: support volta architecture GPUs for the vLLM backend
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 openllm.