Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Python agentaichatgptdeepseekfine-tuninggemmaimage-generationllamallmllmsopenaipythonqwenreinforcement-learningself-hostedstable-diffusiontext-to-speechttsuiunsloth
Fix SDAR empty-mask resampling to match the reference (#13771)
cherry77-cloud1389ec4cbed1
diff --git a/tests/diffusion/test_diffusion_block.py b/tests/diffusion/test_diffusion_block.pyindex 91c7c461e0f..5854c5111a5 100644--- a/tests/diffusion/test_diffusion_block.py+++ b/tests/diffusion/test_diffusion_block.py@@ -253,7 +253,14 @@ def test_noise_ranges_and_prompt_untouched():assert p.min() >= low and p.max() <= highassert not masked[:, :5].any() and torch.equal(noisy == MASK_ID, masked)ratio = masked[:, 5:].float().mean().item()- assert abs(ratio - (low + high) / 2) < 0.02+ expected = (low + high) / 2+ if profile is sdar:+ # Rejection resamples both p and mask; only ten empty draws force one token.+ n = int(maskable[0].sum())+ empty_probability = (1 - low) ** n / (n + 1)+ expected *= sum(empty_probability**attempt for attempt in range(10))+ expected += empty_probability**10 / n+ assert abs(ratio - expected) < 0.02_, masked, _ = sdar.sample_noise(clean[:, :6], maskable[:, :6], MASK_ID, SimpleNamespace())assert masked.any(dim = 1).all() # SDAR masks at least one supervised token per row_, _, p = llada2.sample_noise(clean, maskable, MASK_ID, SimpleNamespace(diffusion_eps = 0.1))diff --git a/unsloth/models/diffusion_block.py b/unsloth/models/diffusion_block.pyindex b7759c0246f..dfd29e7d07b 100644--- a/unsloth/models/diffusion_block.py+++ b/unsloth/models/diffusion_block.py@@ -183,10 +183,21 @@ class BlockDiffusionProfile(DiffusionProfile):"""-> noisy ids, masked bool [B, L], p [B] mask probability per row."""batch, length = clean.shapelow, high = self.noise_range(args)- p = low + (high - low) * torch.rand(batch, device = clean.device)- masked = (torch.rand(batch, length, device = clean.device) < p[:, None]) & maskable- if self.defaults.get("ensure_masked", False):- # Rescue draw taken every step (fixed shape, no host sync); it only changes rows left empty.+ if not self.defaults.get("ensure_masked", False):+ p = low + (high - low) * torch.rand(batch, device = clean.device)+ masked = (torch.rand(batch, length, device = clean.device) < p[:, None]) & maskable+ else:+ # SDAR redraws (p, mask) jointly up to ten times, then forces a token with the last p. All ten+ # draws at once (fixed shape, no host sync); each row keeps its first non-empty one.+ tries = 10+ ps = low + (high - low) * torch.rand(tries, batch, device = clean.device)+ draws = (+ torch.rand(tries, batch, length, device = clean.device) < ps[..., None]+ ) & maskable+ hit = draws.any(dim = 2)+ pick_try = torch.where(hit.any(dim = 0), hit.int().argmax(dim = 0), tries - 1)+ rows = torch.arange(batch, device = clean.device)+ p, masked = ps[pick_try, rows], draws[pick_try, rows]empty = maskable.any(dim = 1) & ~masked.any(dim = 1)scores = torch.rand(batch, length, device = clean.device).masked_fill(~maskable, -1.0)pick = F.one_hot(scores.argmax(dim = 1), length).bool()