Commit History

Autor SHA1 Mensaxe Data
  myhloli 64586d03ea fix: import MinerULogitsProcessor conditionally for vllm-engine and vllm-async-engine backends hai 1 semana
  myhloli cf1fbd2923 fix: enhance device and backend configuration handling in lmdeploy and vlm modules hai 1 semana
  myhloli 0a4c9e307f fix: enhance http-client backend parameters in vlm_analyze.py for improved configuration options hai 2 semanas
  myhloli d2c93b770f fix: refactor backend handling in vlm_analyze.py for improved model loading and error handling hai 2 semanas
  myhloli 3293299f34 fix: update README to clarify Windows LMDeploy backend performance and compatibility hai 2 semanas
  myhloli 39e7aa52a2 fix: improve device type and backend handling in lmdeploy configuration hai 2 semanas
  myhloli a2136c22a5 fix: add backend argument handling and logging for lmdeploy backend configuration hai 3 semanas
  myhloli 3fcca35c73 fix: add Linux environment detection and set lmdeploy backend based on device type hai 3 semanas
  myhloli 5c743dc169 fix: update device handling and backend configuration in analysis scripts hai 3 semanas
  myhloli 85558061ff feat: add lmdeploy backend support and refactor related components hai 3 semanas
  jinminxi104 9ec03c0353 add lmdeploy-backend hai 3 semanas
  myhloli 4afa045545 refactor: update import statement to use check_sys_env and adjust logging level for image loading hai 4 semanas
  myhloli 14c334d2b0 feat: add macOS version check for mlx-engine backend support hai 1 mes
  myhloli 2f1369a877 feat: add Mac environment checks and support for Apple Silicon in backend selection hai 1 mes
  myhloli 6a6c650062 fix: correct spelling of set_default_gpu_memory_utilization and set_default_batch_size functions hai 1 mes
  myhloli 0d0ebfd7bc fix: improve GPU memory utilization handling and ensure OMP_NUM_THREADS is set only if not defined hai 1 mes
  myhloli 078aaaf150 fix: remove unnecessary parameters from kwargs in vlm_analyze.py initialization hai 1 mes
  myhloli c3a55fffab fix: add utility functions for GPU memory utilization and batch size configuration hai 1 mes
  myhloli 0758de6d24 Update vllm version and increase default GPU memory utilization hai 1 mes
  myhloli ea4271ab37 Set OMP_NUM_THREADS environment variable to 1 for vllm backend initialization hai 1 mes
  myhloli 4b480cfcf7 Add max_concurrency parameter to improve backend processing hai 1 mes
  myhloli f1659eb7a7 Refactor logits processor handling in server.py and vlm_analyze.py for improved clarity and consistency hai 2 meses
  myhloli 7c481796f8 Refactor custom logits processors to include vllm version checks and improve logging hai 2 meses
  myhloli f5e0e67545 Add custom logits processors functionality with compute capability check hai 2 meses
  myhloli a4cac624df Add compute capability check for custom logits processors in server.py and vlm_analyze.py hai 2 meses
  myhloli 9fc3d6c742 Remove direct import of MinerULogitsProcessor and add it conditionally in vllm backend hai 2 meses
  myhloli 72f1f5f935 Update mineru-vl-utils version and add logits processors support hai 2 meses
  myhloli 3ca520a3fe feat: implement dynamic batch size calculation based on GPU memory in vlm_analyze.py hai 2 meses
  myhloli 11ebb47891 fix: remove redundant model_path checks for vllm backends in vlm_analyze.py hai 2 meses
  myhloli 7a71cfe288 feat: add support for vllm-async-engine backend in vlm_analyze.py hai 2 meses