Comments (6)
Lzhang-hub
commented on June 24, 2024
5
install nvidia-cublas-cu12==12.3.4.1 after install vllm, vllm default install nvidia-cublas-cu12==12.1.3.1
pip3 install vllm
pip3 install nvidia-cublas-cu12==12.3.4.1
from vllm.
LiaoYuanF
commented on June 24, 2024
和你遇到了相同的Floating point exception问题，请问你有解决吗
from vllm.
fengyizhu
commented on June 24, 2024
+1
from vllm.
cwlseu
commented on June 24, 2024
Encountered a similar issue when deploying Mixtral8x7B using vllm 0.4.2.
from vllm.
peixin-lin
commented on June 24, 2024
Same issue happened to me when deploying with H20.
from vllm.
tohneecao
commented on June 24, 2024
try using cuda-12.3 and cublas12.3.4.1，it works for me
from vllm.
Related Issues (20)
- [Performance]: How use vllm.attention.ops.triton_flash_attention replace flash_attn package HOT 1
- [Bug]: Performance : very slow inference for Mixtral 8x7B Instruct FP8 on H100 with 0.5.0 and 0.5.0.post1 HOT 2
- [Bug]: CUDA illegal memory access error when `enable_prefix_caching=True` HOT 4
- [Bug]: Vllm 0.3.0 got weired output
- [Feature]: LoRA support for Mixtral GPTQ and AWQ HOT 1
- [Feature]: asymmetric tensor parallel
- [Bug]: prefix-caching: inconsistent completions HOT 1
- [Bug]: Distribute Tests PR test fails
- [Bug]: llava-v1.6-mistral-7b-hf prompt template handling error HOT 3
- [Bug]: RuntimeError: CUDA error: no kernel image is available for execution on the device HOT 1
- [Bug]: OOM when setting prompt_logprobs=1 HOT 3
- [RFC]: Refactor Worker and ModelRunner to consolidate control plane communication HOT 10
- [Bug]: Using tensor-parallel-size 4 fails for some models with pyo3_runtime.PanicException: The global thread pool has not been initialized.: ThreadPoolBuildError {"Resource temporarily unavailable" })
- [RFC]: Implement KV cache transferring mechanism in vLLM HOT 2
- [Performance] [Speculative decoding] Speed up autoregressive proposal methods by making sampler CPU serialization optional HOT 2
- [Bug]: Speculative decoding server: `ValueError: could not broadcast input array from shape (513,) into shape (512,)` HOT 11
- [Bug]: Regression in LoRA Adapter loading speed between vllm 0.4.3 and 0.5.0 HOT 3
- [RFC]: Branch based version control, and development version
- [Usage]: how to use marlin kernel for GPTQ model HOT 9
- [Performance]:
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 vllm.