Sergey Penkovsky 2e72dbaf07 test(llama): add unit tests for generation, cache, and edge cases ...

- Covers inference with and without cache and with sampling (top-k, top-p)
- Includes test for max sequence length (should raise ValueError)
- Verifies output shape and absence of dtype errors for the mask logic
- Minimal config and random data ensure tests are fast and robust

Motivation: Regression and integration protection for Llama decoding and sampling logic.

2025-10-15 14:37:35 +03:00

..

test_gpt2.py

test(gpt2): add unit tests for generation, cache behavior, and error conditions

2025-10-15 14:36:32 +03:00

test_gpt.py

refactor(core): refactor RoPE and MultiHeadAttention, add math-rich docs, expand tests, remove unused head_attention

2025-10-15 11:04:07 +03:00

test_llama.py

test(llama): add unit tests for generation, cache, and edge cases

2025-10-15 14:37:35 +03:00

test_mistral.py

test(mistral): add unit tests for model generation and cache

2025-10-15 13:20:50 +03:00