[diffusion] doc: sync CFG and tracing documentation (#39883)

Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>

docs/cookbook/diffusion/MiniMax/MiniMax-H3.mdx

@@ -1342,7 +1342,7 @@ fold decision is not node-boundary aware:
 - V2V uses `task: "ref2va"` with a `video` or `video_audio` reference; it is served by the `Ref2VA` partition and is not a separate public task value.
 - `conditions[].start_time_seconds` selects a non-negative offset for a video reference. Its visual and audio streams are always sought together.
 - Ref2VA condition order is semantic and must match the one-based material tags in the prompt. For Ref2VA, `target.aspect_ratio: "auto"` resolves to the model's 16:9 fallback rather than inheriting a reference asset's geometry.
-- The distilled pipeline uses a single denoising branch, so CFG parallelism does not apply. Do not enable it: `--enable-cfg-parallel true` or `--cfg-parallel-size` greater than 1 is rejected instead of duplicating the positive branch. Explicitly disabling CFG, or setting its size to 1, remains a valid no-op.
+- The distilled pipeline uses a single denoising branch, so CFG parallelism does not apply. Keep it disabled: a CFG degree greater than 1 is accepted for request compatibility, but the extra ranks only recompute the same branch and do not accelerate the request. Explicitly disabling CFG, or setting its size to 1, remains a valid no-op.
 - The released visual VAE quality recipe uses overlapping tiled decode. SGLang keeps that recipe by default and distributes complete tiles across the decode group; this changes scheduling, not the computation inside each tile.
 - H3 rejects `--vae-config.parallel-decode-mode spatial` and `spatial_shard`: validation found output mismatches. Use the default released tiled recipe.
 - Keep the default `--encoder-parallel auto`. With the server’s default `batching_max_size` of 1, single-node H100/H200/B200/B300 recipes with peer-to-peer access fold the Qwen text encoder over otherwise idle Ulysses ranks. This is separate from DiT tensor parallelism. A pure-TP recipe already shards the encoder over its TP group and does not add a world fold.

docs/cookbook/diffusion/SANA-WM/SANA-WM.mdx

@@ -192,7 +192,7 @@ Notes on launch behavior:
 
 - **Default endpoint** is `127.0.0.1:30000` (`--host` / `--port` override).
 - **CPU offload flags are optional.** `--dit-cpu-offload`, `--text-encoder-cpu-offload`, and `--image-encoder-cpu-offload` are available; defaults are auto-adjusted from GPU memory (GPUs under 30 GB get more aggressive offloading).
-- **Multi-GPU realtime.** Prefer explicit sequence parallelism (`--sp-degree` equal to the number of GPUs for a single session). Do not enable CFG parallel for the realtime profile: the default realtime request uses `guidance_scale=1.0`, while CFG parallel requires active cond/uncond branches.
+- **Multi-GPU realtime.** Prefer explicit sequence parallelism (`--sp-degree` equal to the number of GPUs for a single session). Do not enable CFG parallel for the realtime profile: the default request uses `guidance_scale=1.0`, so the extra CFG ranks only recompute the same branch.
 - **FSDP.** Use `--use-fsdp-inference` only when you specifically need weight sharding for memory. For the low-latency realtime profile, prefer keeping components resident and using SP first.
 - **Warmup.** Server warmup is **automatically skipped** for the realtime pipeline — a synthetic warmup request has no WebSocket session, so the server detects the registered realtime adapter and skips it. No explicit `--warmup-mode` setting is needed.
 

docs/docs/sglang-diffusion/api/cli.mdx

@@ -95,7 +95,7 @@ Use `sglang generate --help` and `sglang serve --help` for the full argument lis
 - `--dp-size {N}` (alias `--data-parallel-size`): number of data-parallel replicas. Each replica is a full copy of the engine on `num_gpus / N` GPUs with its own ingress; generation requests round-robin across replicas, realtime sessions stick to the replica holding their state, and control operations (weights, LoRA, memory occupation, shutdown) apply to every replica. Combines with the other parallelism axes (`num_gpus = dp × cfg × tp × sp`); monolithic serving only.
 - `--ulysses-degree {N}` and `--ring-degree {N}`: USP parallelism controls
 - `--kv-gather-degree {N}`: sequence-parallel degree that splits rows inside attention and exchanges with one K/V all-gather (queries stay local) instead of Ulysses all-to-all. Non-causal attention only; does not compose with `--ulysses-degree`/`--ring-degree` yet. When no SP degree is set explicitly, `sp_degree=2` defaults to `kv_gather_degree=2` (its measured-win zone) and higher degrees default to Ulysses; under that auto assignment, attention calls the gather path cannot take fall back to the Ulysses exchange, while an explicit degree fails instead of degrading.
-- `--enable-cfg-parallel {true|false}`: enable or explicitly disable CFG parallelism
+- `--enable-cfg-parallel {true|false}`: enable or explicitly disable CFG parallelism. Requests that disable CFG remain valid on a CFG-parallel server, but extra CFG ranks redundantly recompute the single active branch.
 - `--encoder-parallel {auto|fold|dp|replicate}`: how native encoders use the GPUs in each DiT replica. `auto` TP-folds a native text/image encoder wide enough to benefit, selects batch DP for an explicitly supported native text encoder when it can engage, and otherwise keeps the existing encoder TP layout; `fold` shards native text/image encoders across the full replica whenever dimensions allow; `dp` splits a batched encode across supported native text encoder copies and composes with encoder TP; `replicate` disables folding and batch DP. Encoder collectives never cross `--dp-size` replicas. See [Encoder Parallelism](/docs/sglang-diffusion/encoder_parallel).
 - `--warmup-mode {off|request|server}`: control startup warmup for `sglang serve`; `off` skips warmup, `request` primes the request path, and `server` runs a full synthetic server warmup before serving traffic
 - `--enable-torch-compile {true|false}`: compile native diffusion hot paths. When no warmup mode is configured, this also enables server warmup so first real requests do not pay compile latency.
@@ -110,6 +110,9 @@ Use `sglang generate --help` and `sglang serve --help` for the full argument lis
 - `--srt-encoder-timeout {SECONDS}`: Timeout in seconds for HTTP requests to the SGLang encoder server
 - `--srt-encoder-connection-timeout {SECONDS}`: TCP connection timeout in seconds for SGLang encoder server
 - `--scheduler-rpc-timeout {SECONDS}`: optional end-to-end deadline for an internal scheduler RPC, including scheduler queue time. It is unset by default so valid long-running and queued video jobs are not failed by the transport layer. Set it only when the deployment requires a bounded request deadline; caller cancellation and server shutdown remain effective without it.
+- `--enable-trace`: export OpenTelemetry traces for the diffusion scheduler and worker stages.
+- `--otlp-traces-endpoint {HOST:PORT}`: OTLP collector endpoint used with `--enable-trace` (default: `localhost:4317`).
+- `--otlp-service-name {NAME}`: `service.name` attached to exported traces. Resolution order is this flag, `OTEL_SERVICE_NAME`, then `sglang-diffusion`.
 - `--enable-metrics`: expose Prometheus metrics at `/metrics` (default: disabled). Includes request counts, queue time, host-side stage timing and LoRA state, separated by role and DP replica. See [Production metrics](/docs/sglang-diffusion/production_metrics) for metric semantics and disaggregated scraping.
 - `--pe-server-url {HTTPADDRESS}`: url of SGLang server hosting the PE model (e.g., for ERNIE-Image). See [Models with Prompt Enhancement](/docs/sglang-diffusion/models_with_pe).