vLLM ships day-0 support for Baidu's ERNIE 5.5 Flash Base
The benchmark gap over DeepSeek-V4-Flash-Base in the same evaluation setup makes this one of the stronger open base weights released for coding workloads, and day-0 vLLM support means teams can deploy it without custom serving work. Practitioners running RL research or domain adaptation get open base weights plus serving recipes for expert parallelism, KV offload and prefill/decode disaggregation on GB200 and H100 hardware.
Baidu's ERNIE 5.5 Flash Base is a 280B-parameter open model with 14B active per token, pre-trained on 33.5T tokens with 128K training context and up to 1M tokens for fine-tuning and inference. It scores 82.3% on HumanEval+ and 40.1% on LiveCodeBench pass@1 (1-shot), versus 69.5% and 31.9% for DeepSeek-V4-Flash-Base under the same setup. The architecture uses 37 compressed-attention layers, 6 MLA-DSA layers, Multi-Router Latent MoE, and an ECHO speculative-draft mechanism that reuses the final layer. Weights are available on Hugging Face and ModelScope, and can be served in FP8 or BF16 with the vLLM-ERNIE plugin on vLLM 0.32.0, verified on NVIDIA GB200 and H100.
🎉 Day-0 support for @Baidu_Inc’s ERNIE 5.5 Flash Base with vLLM!
280B total parameters, 14B active per token. Pre-trained on 33.5T tokens, with 128K training context and up to 1M tokens for fine-tuning and inference. Open Base weights for domain adaptation, instruction tuning and RL research.
Code highlights: 82.3% HumanEval+ and 40.1% LiveCodeBench pass@1 (both 1-shot), versus 69.5% and 31.9% for DeepSeek-V4-Flash-Base under the same evaluation setup.
Efficiency is built into the architecture: 37 compressed-attention layers + 6 MLA-DSA layers, Multi-Router Latent MoE, and ECHO — reusing the final layer as a speculative draft.
Serve FP8 or BF16 with Baidu’s vLLM-ERNIE plugin on vLLM 0.32.0. ECHO runs through vLLM’s MTP path; recipes include expert parallelism, KV offload and prefill/decode disaggregation, with runs verified on @NVIDIA GB200 and H100.
Weights are on @huggingface and @ModelScope2022.
Recipe: https://t.co/OhlAm9XYKB FP8: https://t.co/pzNsf3LBb9 BF16: https://t.co/igWS26BQ62
