fix(cp_per_layer_transfer): use absolute chunk_page_start for chunked KV dst mapping

The per-layer KV transfer registration hardcoded chunk_page_start=0 when
filtering CP-shared-KV owned pages. The CP filter's second return (`positions`)
are absolute full-sequence page positions built from chunk_page_start, and the
transfer indexes the FULL-request dst_kv_indices by those absolute positions
(mirroring the monolithic send(), which passes chunk_page_start=index_slice.start
— the cumulative page offset). With start=0, chunk N>0's positions were
chunk-local, so its KV was written onto chunk 0's decode pages, corrupting the
decode output. Non-chunked requests (single chunk, start=0) were unaffected,
matching the observed symptom (non-chunked byte-identical, chunked garbage).

Fix: chunk_page_start = chunk_key // page_size, where chunk_key is the chunk's
start_send_idx (page-aligned), making it exactly the monolithic index_slice.start.

Verified: opus first-principles code audit; empirical mapping-invariant on the
deployed modules (per-chunk == whole-request for all 8 CP ranks; old start=0
sends chunk1 to chunk0's dst); 2 new regression tests (TestChunkedDstMapping).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

python/sglang/srt/disaggregation/mooncake/conn.py

@@ -417,11 +417,19 @@ class MooncakeKVManager(CommonKVManager):
             cp_rank=self.attn_cp_rank,
         )
         pages = np.asarray(page_indices, dtype=np.int32)
+        # chunk_key is this chunk's start_send_idx in TOKENS (page-aligned for any
+        # non-first chunk). The CP filter's `positions` (second return) are absolute
+        # full-sequence page positions built from chunk_page_start, and the transfer
+        # indexes the FULL-request dst_kv_indices by those absolute positions (mirrors
+        # send(): chunk_page_start=index_slice.start, worker: dst_kv_indices[logical_
+        # page_positions]). Must offset by the chunk's absolute page start, else chunk
+        # N>0 writes its KV onto chunk 0's decode pages. page_size divides chunk_key.
+        chunk_page_start = int(chunk_key) // self.kv_args.page_size
         for info in infos.values():
             if getattr(info, "is_dummy", False):
                 continue
             owned_pages, positions = filter_kv_pages_for_cp_shared_kv(
-                layout=layout, logical_pages=pages, chunk_page_start=0
+                layout=layout, logical_pages=pages, chunk_page_start=chunk_page_start
             )
             dst_indices = np.asarray(info.dst_kv_indices, dtype=np.int32)[positions]
             ctx = self.build_per_layer_context(