[Feature]: support LlavaForConditionalGeneration with turbomind inference #2710
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
|
Please resolve the linting error by : pip install pre-commit
cd lmdeploy # the root directory of lmdeploy repo
pre-commit install
pre-commit run --all-files |
deepindeed2022
force-pushed
the
feature/llava_qwen2
branch
from
bf61682 to
20c7476
Compare
lvhan028
reviewed
Nov 5, 2024
lvhan028
reviewed
Nov 5, 2024
irexyc
reviewed
Nov 6, 2024
irexyc
reviewed
Nov 6, 2024
irexyc
reviewed
Nov 6, 2024
AllentDan
reviewed
Nov 6, 2024
AllentDan
reviewed
Nov 7, 2024
AllentDan
reviewed
Nov 7, 2024
irexyc
reviewed
Nov 7, 2024
irexyc
reviewed
Nov 7, 2024
- fix tune attribute error - add chinese llava doc
deepindeed2022
force-pushed
the
feature/llava_qwen2
branch
from
3383c6e to
48d1a5c
Compare
deepindeed2022
changed the title
irexyc
reviewed
Nov 8, 2024
|
从config.json 里面读参数可能不是特别好，尤其是对于这种融合了多个模型的结构，很多参数都省略了，强行加默认值会增加出错的风险，之后可以另外提交PR采用更好的方式。 |
irexyc
approved these changes
Nov 8, 2024
AllentDan
approved these changes
Nov 8, 2024
|
|
AllentDan
pushed a commit
to AllentDan/lmdeploy
that referenced
this pull request
Nov 13, 2024
…ence (InternLM#2710) * feat: support llava_qwen2 for fp16 and awq * update generate gemm config script for VLM * lint: fix lint warning * doc: presenting the usage in the user guide * resolve conflict issue and refactor for better design * fix and doc: - fix tune attribute error - add chinese llava doc * keep LlavaLlamaForCausalLM/LlavaMistralForCausalLM to llama * fix attn_bias default value
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Outdated suggestions cannot be applied.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.
Motivation
Modification
Use cases (Optional)
lmdeploy serve api_server llava_hf/llava_interleave_qwen2_7b_hf