Hy3
Support summary
Hy3 is a checkpoint published by Tencent, built on the HYV3ForCausalLM architecture. Official recipes or cookbooks cover vLLM and SGLang, without pinning a stable release.
- Documented hardware
- NVIDIA / CUDA and AMD / ROCm
- Documented quantization
- BF16
- Documented features
- Multi-token prediction, Reasoning parsers, Speculative decoding, Tensor parallelism, and Tool calling
- Configured context
- 262,144 tokens
- License
- apache-2.0
Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.
Hugging Face model card
- Publisher
- Tencent
- Task
- text generation
- License
- apache-2.0
- Library
- transformers
- Architecture
- HYV3ForCausalLM
- Weight tensor elements
- 298.8B
- Tensor types
- BF16, F32
- Configured context
- 262,144 tokens
- Weight access
- Public
- Repository created
- 2026-07-02
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | Version not pinnedRecipe / cookbook | Documented recipeSource: vllm · models/tencent/Hy3.yamlReviewed | No supported release indexed | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | Version not pinnedRecipe / cookbook | Documented recipeSource 1: sglang · docs/cookbook/autoregressive/Tencent/Hy3.mdxSource 2: sglang · docs/src/snippets/_deployment.jsxSource 3: sglang · docs/src/snippets/configs/tencent/hy3.jsxSource 4: sglang · docs/src/snippets/configs/tencent/hy3-benchmarks.jsxSource 5: sglang · docs/src/snippets/_playground.jsxReviewed | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||