Comments (2)
@QuanhuiGuan Can you share the config.json
with the quantization section here? Maybe there is a groupsize issue that is causing uneven sharding
from vllm.
@QuanhuiGuan Can you share the
config.json
with the quantization section here? Maybe there is a groupsize issue that is causing uneven sharding
here is the config.json file content, i used the offcial AWQ code to quantified my model.
Could you give me some suggestions?
@mgoin
from vllm.
Related Issues (20)
- [Installation]: Build from source: Could NOT find Python. Could not build wheels for vllm. HOT 4
- [Installation]: pip install -e failed HOT 9
- [Usage]: Use quantization=gptq_marlin for faster inference HOT 2
- [Bug]: `flash_attn_cuda.varlen_fwd` may output a bad result when enabling prefix caching HOT 2
- [Bug]: When cuda_graph is enabled, RunTimeError:NCCL error is reported using nvidia-nccl-cu11 HOT 2
- [Usage]: Recommended setting for running vLLM for CPU
- [New Model]: facebook/multi-token-prediction
- [Usage]: RAG HOT 1
- [Bug]: Illegal memory access HOT 2
- [Installation]: poetry add vllm not working on my Mac -- xformers (0.0.26.post1) not supporting PEP 517 builds.
- [Bug]:Qwen2-57B-A14B 两卡 推理报错 HOT 5
- [Bug]: vision chat completion output with odd Instruction/Output prompting. HOT 6
- [Bug]: error: triton_flash_attention.py
- [Usage]: TimeoutError()
- [Misc]: output text is not match with first top_logprobs item on stream mode.
- max_tokens must be at least 1, got -160
- [Performance]: About the use of flash_attn_varlen_func() HOT 1
- [Usage]: NVIDIA多型号的GPU如何利用到? HOT 1
- [Feature]: support torch 2.3.1 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 vllm.