Comments (10)
Due to different kernel selection and kernel implementation, it often generates different results. Unless there are obvious accuracy regression, we think it is reasonable.
from tensorrt-llm.
@byshiue I have seen a significant decrease in the accuracy of the output results of TRT on my test set. I would like to know how you have determined that the output of TRT is reasonable.
from tensorrt-llm.
We use mmlu and summarization task to evaluate. Could you try reproducing the accuracy on public model and public example, sharing your reproduced steps and let us be easier to reproduce your issue?
from tensorrt-llm.
@byshiue Thank you very much for your reply. I'm sorry for the delayed reply. In the past few days, I have been trying to provide a Docker and minimum reproduction code. For the convenience of reproduction, I have upgraded to the latest TRT-LLM(0.11.0.dev2024051400). Now my previous code cannot produce results.
look like this #1632
from tensorrt-llm.
temperature 0.0 is not a valid number in current TensorRT-LLM. Please use greedy search and don't set temperature directly, or set a very small temperature like 1e-6.
from tensorrt-llm.
@byshiue oI modified temperature=1e-6 according to your statement, but I found that errors occur at all times except for the first inference that produces output,self.tokenizer.batch_decode(output_ids[0, :, input_lengths[0] :])will produce error:
like this #1299 。but my trt-version=0.11.
from tensorrt-llm.
Thank you for the try. Could you share the full end to end steps to reproduce your issue? (how to convert ckpt, building engine and run the example)
from tensorrt-llm.
from tensorrt-llm.
Could you share the end to end steps to reproduce your issue? It is hard for me to understand how to use the scripts you share.
from tensorrt-llm.
@byshiue readme.md in zip.I just start webserver for llava-trt to process the result
from tensorrt-llm.
Related Issues (20)
- How to use Medusa to support non llama models? HOT 3
- [Feature]: FlashAttention 3 support HOT 1
- H20 runs python benchmark with enable_cuda_graph encounters cudaDeviceSynchronize runtime error
- Does tensorrt-llm support blip2 with fp8 quantization??
- LLAMA checkpoint ImportError: undefined symbol HOT 5
- [Question] accelerating groupwise weightOnlyGemm on v100 using double buffering? HOT 2
- [Feature] quantize_by_modelopt.py get_tokenizer is not suitable for CodeQwen1.5 7B Chat HOT 2
- Question on how to perform cross-attention with FMHA kernel
- Model Performance Degraded when using BFLOAT16 LoRa Adapters
- Is MPI required even multi device is disabled? HOT 1
- Whisper example crashes with English-only models HOT 2
- better replace submodules update link to ssh
- [model support] please add support minicpm
- 【Doc】Chunk Prefill Doc doesn't exist HOT 1
- How to control out of memory error with PYTORCH_CUDA_ALLOC_CONF? HOT 3
- fused_multihead_attention_v2 CUDA Error: CUDA_ERROR_INVALID_VALUE
- trtllm-build qwen2 0.5B failed HOT 1
- [model support] please support mamba-codestral-7B-v0.1
- FP8 Mixtral 8x7b on NVIDIA L4 (AWS G6) fails "Cannot determine if hopper is specialised without a selected config"
- How to disable KV cache for LLM
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 tensorrt-llm.