Comments (3)
Something like this: model = LLM(..., enable_chunked_prefill=True, max_num_batched_tokens=512, gpu_memory_utilization=0.9)
Try smaller values of gpu_memory_utilization
and/or max_num_batched_tokens
if you still see OOM.
from vllm.
There is a pending PR trying to address this problem: #5355.
Meanwhile, you can try the chunked prefill feature which worked for me as a workaround: https://docs.vllm.ai/en/latest/models/performance.html#chunked-prefill.
from vllm.
would you mind sharing your code? let's say i have n_prompts=10
, and set prompt_logprobs=0
, i'd ideally get the logprobs for all 10 prompts using a single call model.generate(prompts=prompts, sampling_params=sampling_params)
.
from vllm.
Related Issues (20)
- [Bug]: call for stack trace for "Watchdog caught collective operation timeout"
- [Usage]: is there a way to turn off fast attention? a parameter maybe? my model deployment takes 30min to complete HOT 1
- [Usage]: How to use --pipeline-parallel-size HOT 1
- [Bug]: debugging guide for device >= 0 && device < num_gpus INTERNAL ASSERT FAILED at "../aten/src/ATen/cuda/CUDAContext.cpp" HOT 1
- [Usage]: How to use beam search when request OpenAI Completions API HOT 2
- [Bug]: load minicpm model, then get KeyError: 'lm_head.weight'
- [Bug][CI/Build]: Missing attribute 'nvmlDeviceGetHandleByIndex' in AMD tests HOT 1
- [Bug]: Garbled Tokens appears in vllm generation result every time change to new LLM model (Qwen)
- [Bug]: ValidationError using langchain_community.llms.VLLM
- [Installation]: how to disable NCCL support on Jetson cevices HOT 1
- [Bug]: benchmark_serving.py cannot calculate Median TTFT correctly HOT 3
- [Feature]: support Ascend 910B in the future HOT 1
- [New Model]: Lora for Qwen/Qwen2-57B-A14B
- [Usage]: how to initiate the gemma2-27b with a 4-bit quantization? HOT 1
- [Bug]: TypeError in benchmark_serving.py when using --model parameter
- [Gemma 2 27B]: Update docker hub image to support gemma-2-27B-it HOT 1
- [Bug]: Loading LoRA is super slow when using tensor parallel HOT 3
- [Feature]: Add readiness endpoint /ready and return /health earlier (vLLM on Kubernetes) HOT 1
- [RFC]: Priority Scheduling HOT 2
- [Feature]: Add support for interchangable radix attention
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.