Comments (5)
@DarkLight1337 you were quicker by one hour, but you still have failing tests, so I win 😜
from vllm.
It's not a competition xD We can combine our solutions in your PR if need be.
from vllm.
I know! I was being (not so) funny.
from vllm.
I have updated my PR with more test cases. From my understanding, the behaviour of disabling logprobs
and specifying zero top logprobs
should be distinct. In particular:
- Disabling
logprobs
should return nologprobs
at all:- Completions API: Input
logprobs=None
should result in outputtop_logprobs==None
- Chat Completions API: Input
logprobs=False
should result in outputlen(top_logprobs)==0
- Completions API: Input
- Specifying zero top
logprobs
should return thelogprob
for the output token only for Completions API (if it exists):- Completions API: Input
logprobs=0
should result in outputlen(top_logprobs)<=1
- Chat Completions API: Input
logprobs=True,top_logprobs=0
should result in outputlen(top_logprobs)<=k
len(top_logprobs)==0
- Completions API: Input
- Specifying
k
toplogprobs
should return the topk
items, plus thelogprob
for the output token only for Completions API (if it exists):- Completions API: Input
logprobs=k
should result in outputlen(top_logprobs)<=k+1
- Chat Completions API: Input
logprobs=True,top_logprobs=k
should result in outputlen(top_logprobs)<=k+1
len(top_logprobs)==k
- Completions API: Input
Edit: Thanks @br3no for the correction!
from vllm.
My PR #5026 now passes all tests as well.
from vllm.
Related Issues (20)
- [Usage]: Model Qwen2VLForConditionalGeneration does not support LoRA, but LoRA is enabled. HOT 2
- [Installation]: How to install vLLM on Jetson
- [Usage]: Running LLMEngine (or AsyncLLMEngine) in Arrow Flight RPC do_exchange()
- [Installation]: I want to install with CPU follow the guide on windows (wsl2, ubuntu) but the wsl crash. HOT 2
- [Bug]: L40 GPU deepseek-v2 fp8 cuda graph error; Using `--enforce-eager` can run properly. HOT 3
- [Feature]: new possible lora serving implementation? HOT 4
- [Feature]: NotImplementedError: logprobs is not currently supported by the TPU backend
- [Bug]: vllm-cpu docker gguf: AttributeError: '_OpNamespace' '_C' object has no attribute 'ggml_dequantize' HOT 1
- [Installation]: Container image do not build Dockerfile.cpu HOT 3
- [Usage]: Weird vram usage and increase in use HOT 5
- [Usage]: Is DynamicCache supported in vllm? HOT 4
- [Misc]: Speed of serving Starcoder models
- [Usage]: Best engine arguments for large batch inference HOT 2
- [Bug]: (critical bug) random does not work after import vllm HOT 3
- [Feature]: APC introspection interface HOT 1
- [Performance]: Suitable draft model for llama3.1 8b HOT 3
- [Bug]: benchmark_serving.py generates different numbers of tokens at different runs HOT 1
- [Installation]: vLLM build from source errors HOT 11
- [Installation]: Assets v0.6 for cuda 12+ HOT 3
- [Bug]: Model load on 2 or 4-gpu A100 setup may cause default text encoding to be ascii, unless enforce_eager=True HOT 14
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.