| { | |
| "label": "gptq_mtp_routed_experts_v2", | |
| "is_final_quality_preserving": true, | |
| "method": "Frantar-style GPTQ with Cholesky H^-1; per-expert per-group sym INT4 group=128", | |
| "calibration": { | |
| "tokens_processed": 473372, | |
| "expert_token_count_min": 430, | |
| "expert_token_count_max": 175375, | |
| "expert_token_count_mean": 11094.65625, | |
| "n_dump_files": 17701, | |
| "damp_fraction": 0.01 | |
| }, | |
| "simplification_note": "MTP forward replay skipped attention (treated post-attn as identity-residual input); RMSNorms, h_proj/e_proj, gate, and per-expert MLP path are real.", | |
| "measured_draft_acceptance": { | |
| "note": "Weighted draft acceptance from live vLLM speculative-decoding metrics (num_speculative_tokens=1). Output is verifier-exact regardless of acceptance; acceptance affects decode speed only.", | |
| "num_speculative_tokens": 1, | |
| "profiles": { | |
| "general_chat_128k": {"accepted": 2354, "drafted": 3030, "weighted_acceptance": 0.777, "mean_accepted_length": 1.78, "windows": 5}, | |
| "production_262k": {"accepted": 15274, "drafted": 17991, "weighted_acceptance": 0.849, "mean_accepted_length": 1.85, "windows": 25}, | |
| "long_context_262k_research_variant": {"accepted": 319, "drafted": 357, "weighted_acceptance": 0.894, "mean_accepted_length": 1.89, "windows": 3} | |
| }, | |
| "code_heavy_ext10_gate_adapter_assisted": {"weighted_acceptance_range": [0.93, 0.96]} | |
| } | |
| } |