Skip to content

Fix Incorrect Gradients and Illegal Memory Access Error in Mamba2 #537

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Nov 5, 2024
Merged

Fix Incorrect Gradients and Illegal Memory Access Error in Mamba2 #537

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b069d47
Fix incorrect gradients
Hprairie Aug 24, 2024
11c7860
Fix another pointer error in ddAcs_stable
Hprairie Aug 25, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions mamba_ssm/ops/triton/ssd_chunk_scan.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1055,11 +1055,11 @@ def _chunk_scan_bwd_ddAcs_stable_kernel_old(
@triton.autotune(
configs=[
triton.Config({'BLOCK_SIZE_M': 32, 'BLOCK_SIZE_N': 32}, num_stages=3, num_warps=4),
triton.Config({'BLOCK_SIZE_M': 32, 'BLOCK_SIZE_N': 64}, num_stages=3, num_warps=4),
triton.Config({'BLOCK_SIZE_M': 32, 'BLOCK_SIZE_N': 128}, num_stages=3, num_warps=4),
# triton.Config({'BLOCK_SIZE_M': 32, 'BLOCK_SIZE_N': 64}, num_stages=3, num_warps=4),
# triton.Config({'BLOCK_SIZE_M': 32, 'BLOCK_SIZE_N': 128}, num_stages=3, num_warps=4),
triton.Config({'BLOCK_SIZE_M': 64, 'BLOCK_SIZE_N': 32}, num_stages=3, num_warps=4),
triton.Config({'BLOCK_SIZE_M': 64, 'BLOCK_SIZE_N': 64}, num_stages=3, num_warps=4),
triton.Config({'BLOCK_SIZE_M': 64, 'BLOCK_SIZE_N': 128}, num_stages=3, num_warps=4),
# triton.Config({'BLOCK_SIZE_M': 64, 'BLOCK_SIZE_N': 128}, num_stages=3, num_warps=4),
triton.Config({'BLOCK_SIZE_M': 128, 'BLOCK_SIZE_N': 32}, num_stages=3, num_warps=4),
triton.Config({'BLOCK_SIZE_M': 128, 'BLOCK_SIZE_N': 64}, num_stages=3, num_warps=4),
triton.Config({'BLOCK_SIZE_M': 128, 'BLOCK_SIZE_N': 128}, num_stages=3, num_warps=4),
Expand Down Expand Up @@ -1133,7 +1133,7 @@ def _chunk_scan_bwd_ddAcs_stable_kernel(
# If there's seq_idx, we already zero'ed out cb[i, j] for seq_idx[i] != seq_idx[j]
cb = tl.load(cb_ptrs, mask=(offs_m[:, None] < chunk_size) & (offs_n[None, :] < chunk_size - start_n), other=0.0).to(tl.float32)
acc *= cb
dA_cs_n = tl.load(dA_cumsum_ptr + start_n + offs_n * stride_dA_cs_csize, mask=offs_n < chunk_size - start_n, other=0.0).to(tl.float32)
dA_cs_n = tl.load(dA_cumsum_ptr + (start_n + offs_n) * stride_dA_cs_csize, mask=offs_n < chunk_size - start_n, other=0.0).to(tl.float32)
acc *= tl.exp(dA_cs_m[:, None] - dA_cs_n[None, :])
mask = offs_m[:, None] >= start_n + offs_n[None, :] + 1
acc = tl.where(mask, acc, 0.0)
Expand Down