Comments (2)
simon-mo
commented on July 4, 2024
Yes. Although KV cache for a particular request is dynamically allocated. vLLM allocates a continuous memory space for all KV cache ahead of time.
from vllm.
tricky61
commented on July 4, 2024
Yes. Although KV cache for a particular request is dynamically allocated. vLLM allocates a continuous memory space for all KV cache ahead of time.
as the pagedattention has two versions: v1 and v2
In the normal inference, with the increase of max_num_partitions, pagedattention may changed from v1 to v2.
does the Cuda graphs will use two versions? or it will use v1 as default since it is compiled beforehead
from vllm.
Related Issues (20)
- [Usage]: Is this an error ? "async_llm_engine.py:154] Aborted request cmpl-xxxxx"
- [Bug]: "Triton Error [CUDA]: device kernel image is invalid" when loading Mixtral-8x7B-Instruct-v0.1 in fused_moe.py HOT 9
- [RFC]: proper resource cleanup for LLM class with file-like usage HOT 10
- [New Model]: Chameleon support HOT 1
- [Feature]: Support Nemotron-4-340B HOT 1
- [RFC]: Add runtime weight update API HOT 3
- [Usage]: qwen2-1.5b-gptq-in4 single gpu multiprocessing deployment fail
- [Bug]: Two V100 server with a total of 16GPU running Distributed Inference and Serving Vllm with error HOT 7
- [Misc]: how to understand: NUM_ELEMS_PER_THREAD = HEAD_SIZE / THREAD_GROUP_SIZE
- [Bug]: asyncio.exceptions.CancelledError asyncio.exceptions.TimeoutError HOT 1
- api_server.py: error: unrecognized arguments: --tool-use-prompt-template --enable-api-tools --enable-auto-tool-choice HOT 1
- [Bug]: RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling cublasLtMatmul with transpose_mat1 t transpose_mat2 n m 9216 n 3398 k 7168 mat1_ld 7168 mat2_ld 7168 result_ld 9216 computeType 68 scaleType 0
- [Bug]: asyncio.exceptions.CancelledError asyncio.exceptions.TimeoutError HOT 4
- [Feature]: Support for OpenAIEmbeddings with Langchain HOT 8
- [Bug]: which torchvision version required HOT 12
- [Usage]: has vllm supported encoder-only model such as bge-m3?
- [Bug]: VLLM usage on AWS Inferentia instances HOT 6
- [Bug]: KeyError: '/psm_ed65b7e3' HOT 2
- [Feature]: Need CPU inferencing support for non-x86 architectures HOT 2
- [Bug]: 'int' object has no attribute 'expansion'
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.