Comments (3)
@robertgshaw2-neuralmagic I had set params --dtype float16 --lora-dtype auto or float16, but it doesn't work.
from vllm.
Can you double check the precision of the weights?
from vllm.
This should be resolved with the new landed Triton kernels #5036
from vllm.
Related Issues (20)
- [Misc]: Improving VLLM KVCACHE Transfer Efficiency with NCCL P2P Communication HOT 1
- [Feature]: Support block manager v2 for chunked prefill HOT 3
- [Bug]: Phi-3-vision: ERROR 08-09 11:41:40 async_llm_engine.py:56] RuntimeError: stack expects each tensor to be equal size, but got [1933, 4096] at entry 0 and [2509, 4096] at entry 1 HOT 14
- [Bug]: Tensor Parallel > 1 causes desc_act=True GPTQ models to give bad output on ROCm
- [Usage]: Getting empty text using llm.generate of mixtral-8X7b-Instruct AWQ model HOT 1
- [Bug]: prefill/prefix FP8 triton kernel for opt-125m - an illegal memory access was encountered
- [Performance]: vllm inference in CPU instance has generation < 10 tokens / second HOT 2
- [Bug]: LLaMa 3.1 8B/70B/405B all behave poorly and differently using completions API as compared to good chat API HOT 16
- [Bug]: some questions regarding the usage of NCCL allreduce/broadcast/allgather/send/recv in VLLM using pycomm and torch's distributed. HOT 4
- [Bug]: `facebook/chameleon-30b` triggers assertion error while loading weights HOT 2
- [Bug]: Successfully deployed embedding model 'gte-Qwen2-7B-instruct', but got "TypeError: 'async for' requires an object with __aiter__ method, got coroutine" when calling it HOT 3
- [Bug]: guided regex (using outlines and lm format enforcer) return bad error description on invalid regex
- [Bug]: use `openai_vision_api_client.py` get error HOT 1
- [Misc]: Cross-attention QKV computation is inefficient HOT 1
- [Bug]: Bug in vllm/csrc/quantization/awq /gemm_kernels.cu
- [Bug]: Bug in quantization/awq /gemm_kernels.cu gemm_forward_4bit_cuda_m16nXk32 More result have been write HOT 3
- [Bug]: Dockerfile build error HOT 1
- [Usage]: KV Cache Warning for `gemma2` HOT 1
- [RFC]: Refactor the service pipeline to overlap GPU execution and CPU operations
- [Bug]: Pipeline parallelism is only supported through AsyncLLMEngine as performance will be severely degraded otherwise.
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.