DeepSeek-V3/inference
Gabriel Caetano 89882a94f6 Change
Changes:

init_distributed function: Extracted the distributed setup logic into a separate function.
sample function: Modified it to use torch.multinomial instead of an exponentiation-based approach for sampling.
Argument Validation: Replaced the assert with a more user-friendly validation in main to ensure that at least one of the parameters (input-file or interactive) is provided.
Interactive Code Refactoring: The user interaction logic was kept, but the init_distributed function is now called separately at the beginning of main.
2025-01-30 22:47:39 -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 Enhance documentation and update .gitignore for model conversion scripts 2025-01-05 18:18:18 +00:00
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