run end_to_end_test_llama.py error #134
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
hbikki
reviewed
Jun 6, 2023
| ] | ||
|
|
||
| try: | ||
| result = client.infer(model_name, inputs) |
There was a problem hiding this comment.
I see the llama model is decoupled , so shouldn't the call be async_stream_infer instead of infer?
There was a problem hiding this comment.
I correct it to start_stream(call_back（）) and async_stream_infer() and use old input（HttpInferInput）， but got an error "TypeError: Not a cmessage" from tritonclient/grpc/_utils.py
Add llama triton guide
fix the int8_mode and decoupled mode backend support
when i follow the llame_guide.md to build this lib ,this error occur
```bash
/workspace/build/fastertransformer_backend/src/libfastertransformer.cc: In member function 'std::shared_ptr<AbstractTransformerModel> triton::backend::fastertransformer_backend::ModelState::ModelFactory(triton::common::TritonJson::Value&, const string&)':
/workspace/build/fastertransformer_backend/src/libfastertransformer.cc:340:98: error: 'int8_mode' was not declared in this scope
340 | ft_model = std::make_shared<LlamaTritonModel<__nv_bfloat16>>(tp, pp, custom_ar, model_dir, int8_mode);
| ^~~~~~~~~
[100%] Linking CXX executable ../../../../../bin/multi_gpu_gpt_interactive_example
[100%] Built target gptneox_example
[100%] Built target multi_gpu_gpt_triton_example
[100%] Built target llama_example
/workspace/build/fastertransformer_backend/src/libfastertransformer.cc:343:90: error: 'int8_mode' was not declared in this scope
343 | ft_model = std::make_shared<LlamaTritonModel<float>>(tp, pp, custom_ar, model_dir, int8_mode);
```
i think the variable should fix. after i move it , the build success
Update libfastertransformer.cc
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Running python3 tools/end_to_end_test_llama.py, an error was prompted, [400] HTTP end point doesn't support models with decoupled transaction policy