Aug 12 11:34 [FIX] VLLM reasoning with mm: is a part of context Minimax have custom mm: block of reasoning, so i fixed block to exclude it only {{- think_end_token }} is emitted the actual reasoning content is stripped from the prompt sent to the model.
Why: Multi-turn conversations with full reasoning rendered each turn caused context window bloat. Now the model gets a signal (think_end_token) that thinking occurred, but the reasoning text itself is omitted from history to save tokens/context space. Jun 26 17:18 Remove Calibration Dataset section Jun 25 18:01 Add benchmarking parameters (T=1.0, top_p=0.95, max num tokens 65536) and MXFP8 baseline note to Evaluation section Jun 24 22:27 refactor: rename shards to model-NNNNN-of-00088 convention; update index weight_map 16:22 Remove M3 Coding and Agentic Benchmark Results (BF16 baseline) table 08:35 Copy vocab.json from nvidia/MiniMax-M3-NVFP4-Preview0615 08:34 Copy video_processor.py from nvidia/MiniMax-M3-NVFP4-Preview0615 08:34 Copy tokenizer_config.json from nvidia/MiniMax-M3-NVFP4-Preview0615 08:34 Copy tokenizer.json from nvidia/MiniMax-M3-NVFP4-Preview0615 08:34 Copy special_tokens_map.json from nvidia/MiniMax-M3-NVFP4-Preview0615 08:34 Copy processing_minimax.py from nvidia/MiniMax-M3-NVFP4-Preview0615 08:33 Copy preprocessor_config.json from nvidia/MiniMax-M3-NVFP4-Preview0615 08:33 Copy model.safetensors.index.json from nvidia/MiniMax-M3-NVFP4-Preview0615 08:33 Copy merges.txt from nvidia/MiniMax-M3-NVFP4-Preview0615 08:33 Copy image_processor.py from nvidia/MiniMax-M3-NVFP4-Preview0615 08:33 Copy hf_quant_config.json from nvidia/MiniMax-M3-NVFP4-Preview0615 08:33 Copy generation_config.json from nvidia/MiniMax-M3-NVFP4-Preview0615 08:33 Copy experts-layer-059.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 08:30 Copy experts-layer-058.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 08:28 Copy experts-layer-057.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 08:25 Copy experts-layer-056.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 08:23 Copy experts-layer-055.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 08:20 Copy experts-layer-054.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 08:17 Copy experts-layer-053.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 08:15 Copy experts-layer-052.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 08:12 Copy experts-layer-051.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 08:09 Copy experts-layer-050.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 08:07 Copy experts-layer-049.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 08:03 Copy experts-layer-048.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 08:01 Copy experts-layer-047.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:58 Copy experts-layer-046.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:56 Copy experts-layer-045.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:53 Copy experts-layer-044.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:50 Copy experts-layer-043.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:48 Copy experts-layer-042.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:46 docs: note vLLM nightly + PR #46380 required for MiniMax-M3 NVFP4 serving 07:45 Copy experts-layer-041.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:42 Copy experts-layer-040.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:40 Copy experts-layer-039.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:37 Copy experts-layer-038.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:34 Copy experts-layer-037.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:31 Copy experts-layer-036.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:29 Copy experts-layer-035.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:26 Copy experts-layer-034.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:23 Copy experts-layer-033.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:20 Copy experts-layer-032.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:17 Copy experts-layer-031.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:14 Copy experts-layer-030.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:11 Copy experts-layer-029.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 07:09 Copy experts-layer-028.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 
