docs(cookbook): tune GLM-5.2 MTP to 5-1-6 and simplify launch flags (#28448)

docs_new/cookbook/autoregressive/GLM/GLM-5.2.mdx

@@ -92,8 +92,8 @@ import { Playground } from "/src/snippets/_playground.jsx";
 
 ## 2. Configuration Tips
 
-- **DeepSeek Sparse Attention (DSA).** GLM-5.2 uses the `glm_moe_dsa` architecture; SGLang auto-selects the DSA attention backends (`flashmla_sparse` prefill, `fa3` decode, `sgl-kernel` indexer topk). No attention-backend flag is needed on the supported hardware.
-- **MTP / speculative decoding.** The checkpoint ships one nextn layer. Enable EAGLE MTP for lower latency (`--speculative-algorithm EAGLE --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4` for low-latency; `1-1-2` for balanced). The config's `index_share_for_mtp_iteration` reuses the DSA indexer's topk across draft steps (effective only at `--speculative-eagle-topk 1`).
+- **DeepSeek Sparse Attention (DSA).** GLM-5.2 uses the `glm_moe_dsa` architecture; SGLang auto-selects the DSA attention backends (`flashmla_sparse` prefill, `fa3` decode, `sgl-kernel` indexer topk). No attention-backend flag is needed on the supported hardware. SGLang also auto-selects the KV-cache dtype for DSA models — `fp8_e4m3` on Blackwell (B200/GB300/B300, which then routes DSA through the TensorRT-LLM backend) and `bf16` on Hopper (H200) — so no `--kv-cache-dtype` flag is required.
+- **MTP / speculative decoding.** The checkpoint ships one nextn layer. Enable EAGLE MTP for lower latency (`--speculative-algorithm EAGLE --speculative-num-steps 5 --speculative-eagle-topk 1 --speculative-num-draft-tokens 6` for low-latency; `1-1-2` for balanced). The config's `index_share_for_mtp_iteration` reuses the DSA indexer's topk across draft steps (effective only at `--speculative-eagle-topk 1`). **Tune the draft length to the accept length.** GLM-5.2's MTP head is strong — accept length runs high (4+ in many workloads, near-saturating at 5–6 in low-latency runs). Watch the server's reported **accept length** and adjust `--speculative-num-steps` / `--speculative-num-draft-tokens` accordingly: while accept length stays close to the draft-token count there is headroom to push them higher (more accepted tokens per step); if it falls well below, lower them — every rejected draft token is wasted verification compute.
 - **Context Parallelism (CP) for long prefill.** DSA prefill CP splits the long-prefill attention across `--attn-cp-size` ranks. On **Hopper (H200)** this gives a large prefill-latency win at long context — e.g. round-robin CP (`--tp 8 --attn-cp-size 8 --enable-dsa-prefill-context-parallel --dsa-prefill-cp-mode round-robin-split`) cut 64K-token prefill TTFT roughly **2.5–2.8×** vs. plain TP8 in our testing. Trade-offs: CP partitions the KV pool (lower max context at the same `--mem-fraction-static`) and adds some decode-side overhead, so it pays off only for long sequences. **CP is currently verified on Hopper only** — the Blackwell (sm100) DSA-CP FP8 rope kernel is not yet adapted, so leave CP off on B200/GB300.
 - **Memory.** The FP8 weights are large (MoE total, not active params). Start around `--mem-fraction-static 0.8` on H200 (TP8) and tune up; raise it for the 4-GPU GB300 single-node layout (TP4).
 - **DP-Attention + DeepEP** for the balanced/high-throughput strategies spreads attention across data-parallel ranks and routes MoE through DeepEP.