Skip to content

[https://nvbugs/6670516][fix] Call build_kv_page_indices with current signature #18980

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
brb-nv merged 1 commit into from
Sep 10, 2026
+1 −12
Merged

[https://nvbugs/6670516][fix] Call build_kv_page_indices with current signature #18980

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 0 additions & 3 deletions tests/integration/test_lists/waives.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -284,9 +284,6 @@ test_e2e.py::test_ptp_quickstart_advanced_deepseek_r1_w4afp8_8gpus[DeepSeek-R1-W
test_e2e.py::test_ptp_quickstart_bert[TRTLLM-BertForSequenceClassification-bert/bert-base-uncased-yelp-polarity] SKIP (https://nvbugs/6605819)
test_e2e.py::test_ptp_quickstart_bert[VANILLA-BertForSequenceClassification-bert/bert-base-uncased-yelp-polarity] SKIP (bug pending, tracked in PR 17414)
unittest/_torch/attention/sparse/dsa/test_req_idx_per_token.py::test_on_update_kv_lens_rebuilds_stale_map SKIP (https://nvbugs/6574939)
unittest/_torch/attention/sparse/msa/test_minimax_m3_index_decode_score.py::test_index_decode_score_matches_msa_proxy[dtype0] SKIP (https://nvbugs/6669902)
unittest/_torch/attention/sparse/msa/test_minimax_m3_index_decode_score.py::test_index_decode_score_matches_msa_proxy[dtype1] SKIP (https://nvbugs/6669902)
unittest/_torch/attention/sparse/msa/test_minimax_m3_sparse_attn_decode.py::test_sparse_decode_matches_msa_kernel SKIP (https://nvbugs/6669902)
unittest/_torch/attention/sparse/msa/test_msa_backend.py::test_msa_paged_hnd_input_materializes_unaligned_outer_stride SKIP (https://nvbugs/6661846)
unittest/_torch/attention/test_attention_backends.py::test_attention_backend[exaone_moe_gqa_swa128-ctx-bf16-HND-p32-v1] SKIP (https://nvbugs/6668773)
unittest/_torch/attention/test_attention_backends.py::test_attention_backend[qwen2_0_5b_gqa_hd64-ctx-bf16-HND-p32-v1] SKIP (https://nvbugs/6641268)
Expand Down
10 changes: 1 addition & 9 deletions tests/microbenchmarks/minimax_m3_index_decode_score.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,15 +28,7 @@

def _flat_page_table(block_table: torch.Tensor, kv_lens_cpu: torch.Tensor) -> torch.Tensor:
"""Flatten a block table into the per-request page ids fmha_sm100 consumes."""
batch, max_pages = block_table.shape
intra = torch.arange(PAGE_SIZE, dtype=torch.int32)
req_to_token = (block_table.cpu().to(torch.int32) * PAGE_SIZE).unsqueeze(2) + intra
return build_kv_page_indices(
req_to_token.reshape(batch, max_pages * PAGE_SIZE),
torch.arange(batch, dtype=torch.int32),
kv_lens_cpu,
PAGE_SIZE,
)
return build_kv_page_indices(block_table.cpu().to(torch.int32), kv_lens_cpu, PAGE_SIZE)


def _time_us(fn, warmup: int = 20, iters: int = 100) -> float:
Expand Down
Loading