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

[AMD] Document GLM-5.2 MXFP4 recipe update on MI355X (#39230)

Browse Source
This commit is contained in:
Zhang, Jiejing
2026-09-12 15:57:15 -07:00
committed by GitHub
parent 21289cfd50
commit 288627e400
2 changed files with 23 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/src/snippets/configs/zai-org/glm-5.2.jsx
+22 -11
View File
@@ -97,7 +97,7 @@ sgl-eval run aime25 \\
gb300: "lmsysorg/sglang:latest",
b300: "lmsysorg/sglang:latest",
mi355x: "lmsysorg/sglang-rocm:v0.5.13.post1-rocm720-mi35x-20260618",
"mi355x|mxfp4": "lmsysorg/sglang-rocm:v0.5.16-rocm720-mi35x-20260728",
"mi355x|mxfp4": "lmsysorg/sglang-rocm:v0.5.19-rocm720-mi35x-20260910",
mi325x: "lmsysorg/sglang-rocm:v0.5.13.post1-rocm700-mi30x-20260616",
mi300x: "lmsysorg/sglang-rocm:v0.5.13.post1-rocm700-mi30x-20260616",
},
@@ -178,8 +178,12 @@ sgl-eval run aime25 \\
{ id: "mtp-516", label: "EAGLE / MTP 5-1-6 (low-latency)",
flags: ["--speculative-algorithm EAGLE", "--speculative-num-steps 5",
"--speculative-eagle-topk 1", "--speculative-num-draft-tokens 6"],
disable: { hw: ["mi355x", "mi325x", "mi300x"] },
disableReason: "MTP/EAGLE speculative decoding is not yet validated on AMD ROCm (MI300X/MI325X/MI355X): the gfx950 spec-decode draft kernel is not yet validated and at --speculative-num-steps > 3 hits a separate build issue; the DSA nextn draft path is CUDA-only." },
disable: [
{ when: { hw: ["mi300x", "mi325x"] },
reason: "MTP/EAGLE speculative decoding is not yet validated for GLM-5.2 on MI300X or MI325X." },
{ when: { hw: ["mi355x"], quant: ["fp8", "bf16", "nvfp4"] },
reason: "The five-step MI355X recipe is validated only with amd/GLM-5.2-MXFP4." },
] },
{ id: "mtp-112", label: "EAGLE / MTP 1-1-2 (balanced)",
flags: ["--speculative-algorithm EAGLE", "--speculative-num-steps 1",
"--speculative-eagle-topk 1", "--speculative-num-draft-tokens 2"],
@@ -1007,13 +1011,10 @@ sgl-eval run aime25 \\
// weights fit a 4-GPU slice, mirroring the amd/GLM-5.1-MXFP4 MI355X recipe (same DSA
// architecture family) — --trust-remote-code (Quark custom quant config)
// and --kv-cache-dtype fp8_e4m3 both come from that precedent. Pinned to a
// newer image (v0.5.16, see dockerImages["mi355x|mxfp4"]) than the FP8/BF16
// mi355x cells. MTP (mtp-314, steps=3) is validated on MI355X gfx950 with
// this precision — see the mtp-314 cell below. Not yet benchmarked for
// GLM-5.2 on the base strategies → verified:false.
// DSA backend: triton (SGLang's ROCm default). At TP4 this shape hits the
// gfx950 FP8 sparse-MLA tuning; the TP8 FP8/BF16 cells above stay on
// tilelang, where their published numbers were measured.
// newer image (v0.5.19, see dockerImages["mi355x|mxfp4"]) than the FP8/BF16
// mi355x cells. Low-Latency uses validated TP8/EP1; High-Throughput uses
// validated TP4/EP4. Both use five-step MTP from InferenceX PR #2900.
// DSA backend: triton (SGLang's ROCm default).
// ====================================================================
{
match: { hw: "mi355x", variant: "default", quant: "mxfp4", strategy: "low-latency", nodes: "single" },
@@ -1022,10 +1023,15 @@ sgl-eval run aime25 \\
flags: [
"--trust-remote-code",
"--model-path {{MODEL_NAME}}",
"--tp 4",
"--tp 8",
"--ep-size 1",
"--kv-cache-dtype fp8_e4m3",
"--dsa-prefill-backend triton",
"--dsa-decode-backend triton",
"--speculative-algorithm EAGLE",
"--speculative-num-steps 5",
"--speculative-eagle-topk 1",
"--speculative-num-draft-tokens 6",
"--chunked-prefill-size 131072",
"--mem-fraction-static 0.80",
"--watchdog-timeout 1200",
@@ -1061,9 +1067,14 @@ sgl-eval run aime25 \\
"--trust-remote-code",
"--model-path {{MODEL_NAME}}",
"--tp 4",
"--ep-size 4",
"--kv-cache-dtype fp8_e4m3",
"--dsa-prefill-backend triton",
"--dsa-decode-backend triton",
"--speculative-algorithm EAGLE",
"--speculative-num-steps 5",
"--speculative-eagle-topk 1",
"--speculative-num-draft-tokens 6",
"--mem-fraction-static 0.85",
"--cuda-graph-max-bs-decode 256",
"--max-running-requests 256",