Comments (4)
@rkooo567 any possible causes?
from vllm.
To make my suggestion clear,
- # Schedule new prefills.
- remaining_waiting, prefills = self._schedule_prefills(
- self.waiting, budget, curr_loras, enable_chunking=True)
+ if len(remaining_swapped) == 0:
+ # Schedule new prefills.
+ remaining_waiting, prefills = self._schedule_prefills(
+ self.waiting, budget, curr_loras, enable_chunking=True)
on https://github.com/vllm-project/vllm/blob/v0.5.0.post1/vllm/core/scheduler.py#L871-L873 fixes the issue.
However, the condition if len(remaining_swapped) == 0
looks too strict and may affect performance when the most of the requests are n == best_of == 1
. Something like "CPU KV cache usage < 50%" could be better.
from vllm.
I think n>1 creates more sequences, so it is more likely to use swap/preemption (because there's higher pressure to kv cache). Checking remaining_swapped==0 makes sense to me actually. We should prioritize swapped requests over prefill anyway. (and if all swaps are scheduled, remaining swap becomes 0 anyway). @toslunar would you like to create a PR?
from vllm.
Thank you @rkooo567. It makes sense.
I created a PR. The diff is slightly different than my previous comment.
from vllm.
Related Issues (20)
- [Bug]: vllm stuck when using prompt_token_ids and setting prompt_logprobs HOT 4
- [Bug]: Exception in ASGI application HOT 7
- [Misc]: Curious why this is happening: Running phi-3-vision on a RTX 3070 (8GB VRAM) works with transformer but not with vllm (goes out of memory) HOT 3
- [Bug]: Concurrently captioning images with phi3 Vision can cause the backend to crash HOT 3
- [Feature]: Request for SmartSpec Method Support HOT 2
- [Installation]: Wrong torch header file referenced when compiling from source
- [Bug]: Query with logprobs and echo crashes vllm (llama-3-8b-instruct) HOT 1
- [Feature]: Add distributed inference support for lora adapters.
- [Bug]: Incoherent error message when using MLPSpeculator and `num_speculative_tokens` is set too high
- [Bug]: Inconsistent Responses with VLLM When Batch Size > 1 even temperature = 0 HOT 1
- [Misc]: How can I serve multiple models on a single port using the OpenAI API? HOT 3
- [Bug]: TRACKING ISSUE: `AsyncEngineDeadError`
- [Bug]: Internal Server Error when hosting Salesforce/SFR-Embedding-Mistral
- [Bug]: TRACKING ISSUE: CUDA OOM with Logprobs
- [Feature]: Support for google/gemma-2-9b-it / gemma-2-27b-it HOT 1
- [Bug]: FP8 checkpoints with fused linear modules fail to load scales correctly HOT 2
- [Bug]: Model "talking to itself" and ignoring `<|im_end|>` HOT 13
- [New Model]: Florence-2
- Virtual Office Hours: July 9 and July 25
- [Bug]: Illegal memory access for MoE kernel with large workloads 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.