minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[AMD] Enable HiCache for GLM-5.2 MI355X throughput recipe (#40570)

Browse Source
This commit is contained in:
Zhang, Jiejing
2026-09-21 15:28:27 -07:00
committed by GitHub
parent 8bde82c0ad
commit 66f19f5c46
2 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/cookbook/autoregressive/GLM/GLM-5.2.mdx
+1 -1
View File
@@ -124,7 +124,7 @@ import { Playground } from "/src/snippets/_playground.jsx";
**gfx950 block-FP8 accuracy: fixed as of the pinned MI355X image (`v0.5.13.post1-rocm720-mi35x-20260618`).** Earlier SGLang ROCm images miscompiled AMD aiter's `gemm_a8w8_blockscale_bpreshuffle` GEMM on gfx950 (ROCm 7.2): the error was small per layer but compounded across all 78 layers and silently corrupted output — in-context reasoning broke (GSM8K ≈ 0) while short factual prompts still looked fine. The root cause was a gfx950/ROCm-7.2 miscompile of the CK kernel (a packed illegal-type FMA that relied on an LLVM coercion pass removed in ROCm 7.2; non-deterministic wrong rows near tile boundaries). This is resolved in the pinned image and newer: GLM-5.2-FP8 on MI350X/MI355X (gfx950) was re-validated at TP4 and TP8 — **GSM8K ≈ 0.96 (0% invalid)** and **15/15 needle-in-haystack retrieval to ~118K tokens**. **MI300X / MI325X (gfx942) were never affected.** If you must run an older image, treat gfx950 FP8 output as unverified. Background: [sgl-project/sglang#28685](https://github.com/sgl-project/sglang/issues/28685) (analysis) and the upstream CK fix [ROCm/rocm-libraries#8639](https://github.com/ROCm/rocm-libraries/pull/8639) (scalar FMA + accumulator anchor; restores correctness and determinism at -O3).
</Note>
- **MTP / EAGLE speculative decoding on AMD.** Five-step MTP is validated for `amd/GLM-5.2-MXFP4` on MI355X with `lmsysorg/sglang-rocm:v0.5.19-rocm720-mi35x-20260916`. Choose **Low-Latency** for the GPU-resident TP8/EP1 topology, or **High-Throughput** for the TP4/EP4 topology. Both emit `--speculative-num-steps 5 --speculative-eagle-topk 1 --speculative-num-draft-tokens 6` with the Triton DSA prefill and decode backends. The TP4/EP4 InferenceX benchmark adds HiCache DRAM offload, but those host-specific knobs are intentionally omitted from the portable cookbook command. MTP remains unvalidated for GLM-5.2 on MI300X/MI325X and for the other MI355X checkpoint precisions.
- **MTP / EAGLE speculative decoding on AMD.** Five-step MTP is validated for `amd/GLM-5.2-MXFP4` on MI355X with `lmsysorg/sglang-rocm:v0.5.20-rocm720-mi35x-20260920`. Choose **Low-Latency** for TP8/EP1, or **High-Throughput** for TP4/EP4 with HiCache (`--enable-hierarchical-cache --hicache-ratio 1.0`). HiCache uses the default `kernel`, `page_first`, and `write_through` settings. MTP remains unvalidated for GLM-5.2 on MI300X/MI325X and for the other MI355X checkpoint precisions.
## 3. Advanced Usage