DeepSeek-V3/inference
Gabriel Caetano 61790e1653 Update 2
Here are the improvements made to the code for your commit message:

Refactored init_distributed function: Extracted distributed setup logic into a separate function.
Updated sample function: Replaced exponential approach with torch.multinomial for sampling.
Improved argument validation: Replaced assert with a more user-friendly validation in main to ensure at least one parameter (input-file or interactive) is provided.
Refactored interactive mode logic: Maintained user interaction logic but moved init_distributed call to the beginning of main.
2025-01-31 19:33:00 -03:00
..
configs Release DeepSeek-V3 2024-12-26 19:01:57 +08:00
convert.py Enhance documentation and update .gitignore for model conversion scripts 2025-01-05 18:18:18 +00:00
fp8_cast_bf16.py Enhance documentation and update .gitignore for model conversion scripts 2025-01-05 18:18:18 +00:00
generate.py Change 2025-01-30 22:47:39 -03:00
kernel.py Update 2 2025-01-31 19:33:00 -03:00
model.py Updated model.py docstrings 2025-01-05 18:24:31 +00:00
requirements.txt Release DeepSeek-V3 2024-12-26 19:01:57 +08:00