From 574c8e554a5371eca2cbf344764cb241c6ec4efc Mon Sep 17 00:00:00 2001 From: brkirch Date: Tue, 11 Oct 2022 03:32:11 -0400 Subject: Add InvokeAI and lstein to credits, add back CUDA support --- modules/sd_hijack_optimizations.py | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'modules/sd_hijack_optimizations.py') diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py index 2a4ac7e0..f006427f 100644 --- a/modules/sd_hijack_optimizations.py +++ b/modules/sd_hijack_optimizations.py @@ -173,7 +173,20 @@ def einsum_op_tensor_mem(q, k, v, max_tensor_mb): return einsum_op_slice_0(q, k, v, q.shape[0] // div) return einsum_op_slice_1(q, k, v, max(q.shape[1] // div, 1)) +def einsum_op_cuda(q, k, v): + stats = torch.cuda.memory_stats(q.device) + mem_active = stats['active_bytes.all.current'] + mem_reserved = stats['reserved_bytes.all.current'] + mem_free_cuda, _ = torch.cuda.mem_get_info(q.device) + mem_free_torch = mem_reserved - mem_active + mem_free_total = mem_free_cuda + mem_free_torch + # Divide factor of safety as there's copying and fragmentation + return self.einsum_op_tensor_mem(q, k, v, mem_free_total / 3.3 / (1 << 20)) + def einsum_op(q, k, v): + if q.device.type == 'cuda': + return einsum_op_cuda(q, k, v) + if q.device.type == 'mps': if mem_total_gb >= 32: return einsum_op_mps_v1(q, k, v) -- cgit v1.2.3