[Docs] GLM-5.3-Flash cookbook: temporarily remove the DCP option (#40036)

2026-09-17 16:17:25 -07:00
parent 1f0c73e9bd
commit b98a2d1096
3 changed files with 6 additions and 74 deletions
@@ -120,10 +120,6 @@ Keep the checkpoint's KDA lower-bound setting unchanged. In particular, do not o

 On Blackwell, the recipes default to an FP8 KV cache with TRT-LLM DSA: on GB300 this pairing measured 2.9–5.7% higher throughput and about 1.8x the KV token capacity at identical pool bytes, with GSM8K accuracy within noise of BF16. BF16 KV with TileLang DSA remains selectable in the deployment panel and is the default on H100 and H200, where FP8 KV with TRT-LLM DSA is disabled. Switch the dtype and both DSA backends together; TileLang DSA with FP8 KV is not a valid CUDA combination.

-### Decode context parallelism
-
-Decode context parallelism (DCP) shards the KV across GPUs during decode to cut long-context latency. The **Context Parallelism** row offers DCP4, validated on 4x GB300 with both KV pairings on the earlier TP4/EP4 recipe and queued for re-measurement on the current command; it requires the current release image, which carries the TileLang LSE fix. Other platforms and attention backends are unvalidated, and draft-extend v2 is unsupported under DCP.
-
 ### Extend the cache hierarchy

 Keep **HiCache** off when GPU memory is sufficient. Select **L1 + L2** to spill reusable cache entries into host memory. Select **+ L3** only after configuring Mooncake on every serving node; the generated command exposes the required configuration path. These options remain selectable but are marked **Not Verified** until the resulting command is validated on the chosen hardware.