MCPcopy Create free account
hub / github.com/FlashSampling/FlashSampling / test_gemv

Function test_gemv

tests/test_gemv.py:6–15  ·  view source on GitHub ↗
()

Source from the content-addressed store, hash-verified

4
5
6def test_gemv():
7 device = torch.device("cuda")
8 hidden_size = 4096
9 vocab_size = 128_000
10 hidden_states = torch.randn(hidden_size, device=device)
11 weights = torch.randn(hidden_size, vocab_size, device=device)
12 expected = hidden_states @ weights
13
14 tl_result = tl_gemv(hidden_states, weights)
15 assert torch.cosine_similarity(expected, tl_result, dim=0) > 0.99

Callers

nothing calls this directly

Calls 1

tl_gemvFunction · 0.90

Tested by

no test coverage detected