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

Add GLM-5.3-Flash cookbook (#36440)

Browse Source
This commit is contained in:
Xinyuan Tong
2026-08-26 07:00:16 -07:00
committed by GitHub
parent 8eaffdf382
commit dfc40e0efe
6 changed files with 850 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/cookbook/autoregressive/GLM/GLM-5.2.mdx
-1
View File
@@ -1,7 +1,6 @@
---
title: GLM-5.2
description: "Deploy GLM-5.2 with SGLang — Z.ai's DeepSeek-Sparse-Attention (DSA) Mixture-of-Experts model with MTP speculative decoding and 1M context, on H200, B200, B300, GB300, and AMD MI300X/MI325X/MI355X."
tag: NEW
---
## Deployment
docs/cookbook/autoregressive/GLM/GLM-5.3-Flash.mdx
+250
View File
@@ -0,0 +1,250 @@
---
title: GLM-5.3-Flash
description: "Deploy GLM-5.3-Flash with SGLang using recipes for H100, H200, B200, B300, GB200, and GB300, with MTP and multimodal serving."
tag: NEW
---
## Deployment
<a id="install" />
<Accordion title="Install SGLang">
Use an SGLang build that includes GLM-5.3-Flash support.
```bash Command
docker pull lmsysorg/sglang:glm-5.3-flash
```
The deployment panel can render a complete `docker run` command for the selected hardware and options. See [Install SGLang with Docker](/docs/get-started/install#method-3-using-docker) for host setup.
</Accordion>
Choose your hardware, then choose the operating point that matches your workload:
- **Low Latency** starts with adaptive MTP 5/1/6 speculative decoding and tensor parallelism to shorten interactive responses.
- **High Throughput** starts with speculative decoding off, which avoids draft-and-verify overhead under sustained batches.
Every listed hardware platform exposes both strategies. A **Verified** badge means that exact hardware and command were tested. **Not Verified** means the command is a supported starting point that still needs workload validation. A choice is disabled only when the underlying runtime combination is known to be unsupported.
The recommended selection is only a starting point. The same panel also lets you override the KV/DSA pairing, multimodal feature transport, and HiCache tiers. Changing an option that was not part of the measured command changes the badge to **Not Verified** without hiding the option.
import { Deployment } from "/src/snippets/_deployment.jsx";
import { config } from "/src/snippets/configs/zai-org/glm-5.3-flash.jsx";
import { benchmarks } from "/src/snippets/configs/zai-org/glm-5.3-flash-benchmarks.jsx";
<Deployment config={config} benchmarks={benchmarks} />
## Playground
Use the Playground for lower-level tuning such as attention parallelism, MoE communication, and reasoning or tool parsers. It inherits every selection from the deployment panel and shows only the command-line diff.
import { Playground } from "/src/snippets/_playground.jsx";
<Playground config={config} />
## 1. Model introduction
GLM-5.3-Flash is a natively multimodal Mixture-of-Experts model built around a hybrid attention architecture — 320B total parameters with 18B active. Its 45 text layers combine MLA attention, DSA sparse attention, and KDA linear attention, and a 24-layer vision encoder handles image and video input. The checkpoint uses 288 routed experts with 8 active experts per token and includes a native MTP draft layer for speculative decoding. See the [GLM-5.3-Flash blog](https://z.ai/blog/glm-5.3-flash) and the [GLM-5 technical report](https://arxiv.org/abs/2602.15763) for training details.
<table style={{width: "100%", borderCollapse: "collapse", tableLayout: "fixed"}}>
<colgroup>
<col style={{width: "28%"}} />
<col style={{width: "72%"}} />
</colgroup>
<thead>
<tr style={{borderBottom: "2px solid #d55816"}}>
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700}}>Attribute</th>
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700}}>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>Architecture</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>MoE with hybrid attention (MLA, DSA, KDA), mHC, and MTP — 320B total / 18B active parameters</td>
</tr>
<tr>
<td style={{padding: "9px 12px"}}>Precision</td>
<td style={{padding: "9px 12px"}}>FP8 weights with BF16 KV cache by default</td>
</tr>
<tr>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>Context</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>1M tokens</td>
</tr>
<tr>
<td style={{padding: "9px 12px"}}>Inputs</td>
<td style={{padding: "9px 12px"}}>Text, image, and video</td>
</tr>
<tr>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>Generation defaults</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><code>temperature=1.0</code>, <code>top_p=0.95</code>, thinking enabled</td>
</tr>
</tbody>
</table>
The deployment recipes use the checkpoint's generation configuration. Override sampling only when your application has its own evaluated settings.
## 2. Configuration tips
### Choose a strategy
Start with **Low Latency** for chat and agent workloads. Adaptive MTP changes the draft depth as acceptance changes, reducing unnecessary draft work when the server is busy. Measure **High Throughput** for heavily batched traffic where disabling speculative decoding can be more efficient. SGLang serves MTP through `--speculative-algorithm NEXTN`, so generated commands use that flag value.
Strategy labels describe the workload goal, not a hardware restriction. Both strategies stay available when you switch hardware; only the verification badge changes.
### Size both memory pools
GLM-5.3-Flash maintains a paged KV pool for attention and a separate KDA state pool. The KDA state pool can limit concurrency before the KV pool is full. If startup reduces `max_running_requests` because of KDA state capacity, increase `--mamba-full-memory-ratio` or set `--max-mamba-cache-size` for the expected concurrency, then tune `--max-running-requests` to the workload.
Keep the prefix cache enabled for every strategy.
Keep the checkpoint's KDA lower-bound setting unchanged. In particular, do not override `linear_lower_bound` through `--json-model-override-args`.
### Keep the KV and DSA backends paired
The default recipe pairs a BF16 KV cache with TileLang DSA. On Blackwell GPUs, the deployment panel also offers FP8 KV with TRT-LLM DSA as a memory-saving option. Switch the dtype and both DSA backends together; TileLang DSA with FP8 KV is not a valid CUDA combination. FP8 KV with TRT-LLM DSA is disabled on H100 and H200.
### 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.
### Multimodal memory
All strategies enable multimodal serving. The processor samples video at 2 FPS and caps video input at 240,000 visual tokens. Install `torchcodec` in the serving environment before sending video requests. For very long videos on 4x GB300, use encoder disaggregation to isolate the vision encoder's memory spikes from language decoding.
The default multimodal feature transport is automatic, and on a single CUDA node auto resolves to CPU transport. CUDA IPC is opt-in: pass `--mm-feature-transport cuda_ipc` when lower transfer latency matters more than the GPU memory the IPC pool reserves. CUDA VMM transport applies only to multi-node GB200/GB300 systems on the MNNVL fabric, where auto selects it.
## 3. Advanced usage
### 3.1 Reasoning
Thinking is enabled by the checkpoint's generation configuration, and generated commands enable `--reasoning-parser glm45` by default. The OpenAI-compatible API then places thinking in `message.reasoning_content` and the final answer in `message.content`. You can disable **Reasoning Parser** in the Playground when an integration needs the raw response format.
To disable thinking for a request, pass `chat_template_kwargs: {"thinking": false}` in the request body.
### 3.2 Tool calling
Generated commands enable `--tool-call-parser glm47` by default, so structured calls are returned in `message.tool_calls`. You can disable **Tool Call Parser** in the Playground when tool calling is not needed. On follow-up turns, read both `reasoning_content` and `content` because a thinking model can use either field around tool execution.
### 3.3 Multimodal serving
The base recipes accept image and video content through the OpenAI-compatible chat API. Keep the processor defaults unless you have measured a different sampling or resize policy. Inputs above the video token budget are clamped to the processor's limit rather than rejected.
### 3.4 Encoder disaggregation
Encoder disaggregation separates vision preprocessing from language inference. The verified topology uses one 4x GB300 node shared by an encoder-only TP4 process on port 30001 and a language-only TP4/EP4 process on port 30000. Start the encoder first.
<Accordion title="Encoder server (GB300)">
```bash Command
sglang serve \
--model-path zai-org/GLM-5.3-Flash \
--tp-size 4 \
--encoder-only \
--host 0.0.0.0 \
--port 30001
```
</Accordion>
<Accordion title="Language server (GB300)">
```bash Command
sglang serve \
--model-path zai-org/GLM-5.3-Flash \
--tp-size 4 \
--ep-size 4 \
--attention-backend dsa \
--dsa-prefill-backend tilelang \
--dsa-decode-backend tilelang \
--linear-attn-backend triton \
--kv-cache-dtype bfloat16 \
--quantization fp8 \
--moe-runner-backend deep_gemm \
--max-running-requests 64 \
--chunked-prefill-size 8192 \
--max-prefill-tokens 8192 \
--disable-shared-experts-fusion \
--disable-prefill-cuda-graph \
--speculative-algorithm NEXTN \
--speculative-num-steps 3 \
--speculative-eagle-topk 1 \
--speculative-num-draft-tokens 4 \
--speculative-adaptive \
--language-only \
--encoder-urls http://localhost:30001 \
--mem-fraction-static 0.78 \
--host 0.0.0.0 \
--port 30000
```
</Accordion>
This topology served image requests and videos up to 238,080 visual tokens. In a concurrent long-video workload, the largest observed decode gap fell from 5.53 seconds in unified serving to 1.79 seconds with encoder disaggregation. Keep `--mem-fraction-static 0.78` on the language process so the encoder retains room for vision workspaces.
Install `torchcodec` for video and see the [encoder disaggregation guide](/docs/advanced_features/epd_disaggregation) for the generic architecture and operational model.
### 3.5 PD disaggregation (preview)
PD splits prefill and decode into separate server groups behind a router. For this hybrid model, the transfer moves both the paged DSA KV and the KDA recurrent state.
<Warning>
PD serving is mechanically validated with dummy weights only — startup, bootstrap, state transfer, and request flow all work on 4x GB300. It has not been load- or accuracy-tested. Treat it as a preview until the real-weight gate completes.
</Warning>
<Accordion title="PD serving on 4x GB300 (single node)">
```bash Prefill (GPU 0-1)
sglang serve \
--model-path zai-org/GLM-5.3-Flash \
--tp-size 2 \
--dsa-prefill-backend tilelang \
--dsa-decode-backend tilelang \
--kv-cache-dtype bfloat16 \
--moe-runner-backend triton \
--disaggregation-mode prefill \
--disaggregation-bootstrap-port 8998 \
--disaggregation-transfer-backend nixl \
--host 0.0.0.0 \
--port 31000
```
```bash Decode (GPU 2-3)
sglang serve \
--model-path zai-org/GLM-5.3-Flash \
--tp-size 2 \
--base-gpu-id 2 \
--dsa-prefill-backend tilelang \
--dsa-decode-backend tilelang \
--kv-cache-dtype bfloat16 \
--moe-runner-backend triton \
--disaggregation-mode decode \
--disaggregation-transfer-backend nixl \
--host 0.0.0.0 \
--port 32000
```
```bash Router
python -m sglang_router.launch_router \
--pd-disaggregation \
--mini-lb \
--prefill http://127.0.0.1:31000 8998 \
--decode http://127.0.0.1:32000 \
--host 0.0.0.0 \
--port 30000
```
The positional `8998` after `--prefill` must equal the prefill server's `--disaggregation-bootstrap-port`.
</Accordion>
Operational notes:
- Give each role a distinct `--nccl-port` when both share one node.
- Single-node NIXL needs `UCX_NET_DEVICES=lo` and `UCX_TLS=tcp,cuda_copy,cuda_ipc,self,sm` in both server environments.
- The validated arm used the triton MoE runner; deep_gemm under PD is untested.
Known limitations:
- Speculative decoding does not start under PD at the current cut (draft-graph capture width assert on the prefill role; decode-side memory pressure at TP2). Run PD without speculative flags.
- Prefill and decode with different TP sizes transfer state through slice paths, but numeric correctness is unverified. Keep both roles at the same TP size.