THE SOURCE IN CONTEXT
The pinned GLM-5.3 recipe defaults to zai-org/GLM-5.3 (fp8). Its effective default-variant minimum is vLLM 0.29.0. Select the exact variant, hardware override and topology before treating it as a launch plan. No deployment was run by this site.
Which artifact and engine does this recipe select?
The recipe identifies zai-org/GLM-5.3 as its model family entry and selects zai-org/GLM-5.3 by default. The default precision label is fp8; model-wide and variant-specific runtime requirements are kept separately below. The document revision fixes what the recipe said, while the weight revision and executed runtime revision remain separate fields. A model-family title alone cannot establish either artifact identity.
Source: vllm-project · pinned document
What needs special attention for this model?
This is the full model rather than Flash. The base FP8 KV setting and the target precision are different quantities. Check the hardware override, tool parser and reasoning effort with the chosen artifact. The recipe’s 893 GB planning minimum cannot predict the usable context, concurrency or peak allocation of an eight-GPU deployment.
Source: vllm-project · pinned document
How should the settings be applied?
Choose one artifact variant and one hardware profile from the original recipe, then resolve its shared, variant, hardware, strategy and optional-feature settings together. The base arguments listed here are only one layer and are deliberately not presented as a complete runnable command. Check any nightly-image requirement and the model’s parsers before loading weights. A context declaration is a model limit, while batched-token and sequence settings control a serving workload.
Source: vllm-project · pinned document
What does the memory number mean?
The GB figure is the recipe’s declared planning minimum for the selected variant. It is not a site measurement, a universal peak allocation or a promise of maximum context. KV cache, auxiliary/draft models, image encoders, temporary workspace and active requests still require memory. Keep GB and GiB distinct, and use the actual artifact size and runtime allocation for a machine-specific budget.
Source: vllm-project · pinned document
What is needed to reproduce a deployment?
Save the model and conversion revisions, weight hashes, tokenizer/template, container or runtime digest, device count/topology and complete resolved launch. First check one short public request. For a subsequent measurement, fix input and output counts, concurrency, cache state, warmup, sampling, reasoning effort, repetitions and failures. The declarations on this page are source configuration facts; no throughput or quality outcome follows from them.
Source: vllm-project · pinned document
What does the source specify?
These declarations belong to the cited document. A planning minimum, model limit and measured runtime allocation are different quantities.
| Architecture | moe |
|---|---|
| Total parameters as counted by recipe | 743B |
| Active parameters as counted by recipe | 39B |
| Native context declaration (tokens) | 1048576 |
| Model-wide minimum vLLM | 0.29.0 |
| Effective default-variant minimum vLLM | 0.29.0 |
| Default artifact | zai-org/GLM-5.3 |
| Default precision label | fp8 |
| Default planning minimum (GB; recipe declaration) | 893 |
| Default variant hardware allowlist | Not specified |
| Shared base arguments (incomplete launch) | ["--kv-cache-dtype", "fp8_e4m3"] |
| Declared compatible strategies | ["single_node_tp", "single_node_tep", "multi_node_tp", "multi_node_tp_pp", "multi_node_tep", "multi_node_dep", "pd_cluster"] |
| Optional feature names | ["tool_calling", "reasoning", "spec_decoding"] |
| Features selected by default | ["spec_decoding"] |
AI-assisted source reading and original editorial synthesis; no independent model execution.