 Xiaomeng Zhao
|
79f2d03d32
Merge pull request #3990 from myhloli/dev
|
3 주 전 |
|
myhloli
|
d2c93b770f
fix: refactor backend handling in vlm_analyze.py for improved model loading and error handling
|
3 주 전 |
|
myhloli
|
bb25385097
fix: update docker_deployment.md to use 'mineru:latest' instead of 'mineru-vllm:latest'
|
3 주 전 |
|
myhloli
|
60c5f7d890
feat: add mineru-lmdeploy-server service to compose.yaml with configuration
|
3 주 전 |
|
myhloli
|
3293299f34
fix: update README to clarify Windows LMDeploy backend performance and compatibility
|
3 주 전 |
|
myhloli
|
6581af72b4
fix: update README to clarify Windows LMDeploy backend performance and compatibility
|
3 주 전 |
|
myhloli
|
4ba9c73458
feat: add Dockerfiles for camb and maca environments, update ppu base image
|
3 주 전 |
|
myhloli
|
f7509e7dc9
feat: add Dockerfiles for NPU and PPU environments with necessary dependencies
|
3 주 전 |
|
myhloli
|
19c2a6612b
fix: enhance argument handling for device type and backend in lmdeploy server
|
3 주 전 |
|
myhloli
|
1b440a8e92
fix: enhance argument handling for device type and backend in lmdeploy server
|
3 주 전 |
|
myhloli
|
39e7aa52a2
fix: improve device type and backend handling in lmdeploy configuration
|
3 주 전 |
|
myhloli
|
0c8e004874
fix: remove unused variable in set_lmdeploy_backend function
|
3 주 전 |
|
myhloli
|
f9f67ddef4
fix: remove unused variable in set_lmdeploy_backend function
|
3 주 전 |
|
Xiaomeng Zhao
|
2ac829ca32
Merge pull request #3980 from myhloli/dev
|
3 주 전 |
|
myhloli
|
6bafca0555
fix: disable tokenizers parallelism in lmdeploy server configuration
|
3 주 전 |
|
myhloli
|
7516d3ddf4
fix: disable tokenizers parallelism in lmdeploy server configuration
|
3 주 전 |
|
myhloli
|
a2136c22a5
fix: add backend argument handling and logging for lmdeploy backend configuration
|
3 주 전 |
|
myhloli
|
3fcca35c73
fix: add Linux environment detection and set lmdeploy backend based on device type
|
3 주 전 |
|
myhloli
|
6c27bc7f53
fix: update README files to include lmdeploy-engine and adjust accuracy details
|
3 주 전 |
|
Xiaomeng Zhao
|
30f1db6e6d
Merge pull request #3976 from opendatalab/add_lmdeploy_backend
|
3 주 전 |
|
Xiaomeng Zhao
|
e80e53d4de
Merge pull request #3975 from myhloli/add_lmdeploy_backend
|
3 주 전 |
|
myhloli
|
8e5a780fc6
fix: clarify engine descriptions in client.py documentation
|
3 주 전 |
|
myhloli
|
ad35f0bbc2
fix: clarify engine descriptions in client.py documentation
|
3 주 전 |
|
myhloli
|
5c743dc169
fix: update device handling and backend configuration in analysis scripts
|
3 주 전 |
|
Xiaomeng Zhao
|
b26338d0ef
Merge pull request #3974 from opendatalab/add_lmdeploy_backend
|
3 주 전 |
|
Xiaomeng Zhao
|
275ae04e56
Merge pull request #3972 from myhloli/add_lmdeploy_backend
|
3 주 전 |
|
myhloli
|
672e252506
fix: set default device type to 'cuda' in lmdeploy server
|
3 주 전 |
|
myhloli
|
85558061ff
feat: add lmdeploy backend support and refactor related components
|
3 주 전 |
|
Xiaomeng Zhao
|
b4c8a017ea
Merge pull request #3964 from opendatalab/dev
|
3 주 전 |
|
Xiaomeng Zhao
|
5c8d05e076
Merge pull request #3963 from myhloli/dev
|
3 주 전 |
