Comments (5)
i have tried engine_use_ray = True in AsyncEngineArgs or CUDA_VISIBLE_DEVICES = 0,1 but it still does not work ,GPU0 OOM
from vllm.
use tensor-parallel-size
from vllm.
thk, the problem that GPU0 OOM is solved, but new problem comes ,it shows " ValueError: When using LoRA, vocab size must be 32000 >= vocab_size <= 33024 " ,anybody can load the yi-34B-chat with lora successfuly? hoping your suggestion
from vllm.
thk, the problem that GPU0 OOM is solved, but new problem comes ,it shows " ValueError: When using LoRA, vocab size must be 32000 >= vocab_size <= 33024 " ,anybody can load the yi-34B-chat with lora successfuly? hoping your suggestioncu
maybe use max-model-len?
from vllm.
thk, the problem that GPU0 OOM is solved, but new problem comes ,it shows " ValueError: When using LoRA, vocab size must be 32000 >= vocab_size <= 33024 " ,anybody can load the yi-34B-chat with lora successfuly? hoping your suggestion
"ValueError: When using LoRA, vocab size must be 32000 >= vocab_size <= 33024" has already been resolved by #4015. You can build the source from the main branch or wait for the 0.4.1 release. After resolving this issue, Yi-34 can load LoRA successfully.
from vllm.
Related Issues (20)
- [Bug]: OpenAI LogProbs format for Chat-Completion is incorrect HOT 5
- [New Model]: tiiuae/falcon-11B
- [Usage]: Run local models using vLLM HOT 1
- [Bug]: enable_chunked_prefill feature hangs on AMD Radeon PRO W7900 (gfx1100) HOT 4
- [Bug]: inferences are not the same with batch mode when using
- [Help wanted] [Spec decode]: Increase acceptance rate via Medusa's typical acceptance HOT 1
- [Feature] [Spec decode]: Combine chunked prefill with speculative decoding
- [Bug]: UnboundLocalError: local variable 'lora_b_k' referenced before assignment HOT 3
- [Bug]: Mistral 7b inst v0.3 fails to run HOT 1
- [Bug]: HOT 2
- [Usage]: I use llama3. I found that one token is 'Ġor' in tokenizer.get_vocab(). But when I use vllm server, I got ' or' in response. HOT 1
- [Bug]: Command-R incorrect output contains `<EOS_TOKEN>` and seems to do text prediction rather than conversation
- [Misc]: LLM is responding with advertisement HOT 1
- [Bug]: 英伟达最新驱动555.85,vllm运行报错 HOT 2
- [Feature]: Additional metrics to enable better autoscaling / load balancing of vLLM servers in Kubernetes HOT 4
- [Misc]: Understanding Batching Mechanism in Prefill and Decode Phases
- [Installation]:
- [Feature]: Add num_requests_preempted metric HOT 1
- Running Vllm on ray cluster, logging stuck at loading
- [Feature]: multi-steps model_runner?
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.