chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

Keep CP compose on CUDA IPC after syh rebasing

Browse Source 
The syh branch still passed symm writer metadata into the RAGGED MLA
partial-current compose path. After rebasing the CUDA IPC staging path,
those keyword arguments no longer belong to the runtime contract and would
raise at runtime before reaching the IPC compose implementation.

Constraint: Main-stream CP shared-KV compose should use the measured CUDA IPC staging path; symm remains an experimental/benchmark path.
Rejected: Keep writer-rank arguments behind the symm env | the runtime signature has been restored to the IPC contract and the env-gated symm compose is not the production default.
Confidence: high
Scope-risk: narrow
Tested: python -m py_compile nsa_backend.py cp_shared_kv_runtime.py cp_shared_kv_prefetch.py nsa_indexer.py
Not-tested: Local pytest blocked by missing orjson in this environment; remote CUDA/ETE not run in this step
This commit is contained in:
laoyao0822
2026-06-13 01:02:56 +08:00
parent 4d5c7f32d6
commit e0c388076e
1 changed files with 0 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
python/sglang/srt/layers/attention/nsa_backend.py
View File

@@ -37,7 +37,6 @@ from sglang.srt.layers.attention.nsa.cp_shared_kv_runtime import (
mask_batch_logical_pages_to_valid_lengths,
materialize_prefix_and_reuse_current_kv_page_slots,
materialize_shared_token_kv_buffer,
maybe_build_current_page_writer_ranks,
pack_current_mla_kv_for_reuse,
tensor_debug_checksum,
tensor_debug_summary,
@@ -2115,19 +2114,6 @@ class NativeSparseAttnBackend(
current_slot_spans=current_slot_spans,
layer_id=layer.layer_id,
nvtx_source="mla.current_only_page_slots",
current_page_writer_ranks=(
maybe_build_current_page_writer_ranks(
forward_batch=forward_batch,
prefix_lens_cpu=getattr(
forward_batch, "extend_prefix_lens_cpu", None
),
extend_lens_cpu=getattr(
forward_batch, "extend_seq_lens_cpu", None
),
page_size=page_size,
layout=forward_batch.cp_shared_kv_layout,
)
),
)
)
else:
@@ -2274,15 +2260,6 @@ class NativeSparseAttnBackend(
prefix_slot_spans=prefix_slot_spans,
current_slot_spans=current_slot_spans,
layer_id=layer.layer_id,
current_page_writer_ranks=(
maybe_build_current_page_writer_ranks(
forward_batch=forward_batch,
prefix_lens_cpu=prefix_lens_cpu,
extend_lens_cpu=extend_lens_cpu,
page_size=page_size,
layout=forward_batch.cp_shared_kv_layout,
)
),
)
)
if (