finalize pinned NVFP4A16 checkpoint metadata

README.md

@@ -41,26 +41,43 @@ calibration and quality-validation run.
 
 ## Runtime validation (2026-07-27 UTC)
 
-A purpose-built **vLLM one-layer routed-MoE smoke test passed** for this
-published artifact. The harness used vLLM's official compressed-tensors
-NVFP4A16 parameter layout, post-load conversion, fused-MoE method, and SiTU
-activation; it was not the full vLLM model loader or full K3 graph.
+A **complete Stable LatentMoE block passed on vLLM for this published
+artifact** using the official `KimiMoE` class. The test first loaded and ran the
+block through a purpose-built layout path, then rebuilt it and loaded the same
+8,072 source tensors through the real K3 model-class chain:
+`KimiK3ForConditionalGeneration.load_weights` -> `AutoWeightsLoader` ->
+`KimiLinearForCausalLM.load_weights` -> `KimiLinearModel.load_weights` -> the
+generic `process_weights_after_loading` traversal.
 
-- Evidence run: `20260727T220141Z`
+- Evidence run: `20260727T234215Z`
+- Earlier routed-expert-core run: `20260727T220141Z`
 - Tested artifact revision: `8c22f32993e94e063cb634a03b7fc2f9ff539621`
 - Checkpoint shard: `model-00049-of-000096.safetensors` (17,916,197,160 bytes)
 - Runtime image: `vllm/vllm-openai:kimi-k3`
 - Pinned linux/amd64 image: `vllm/vllm-openai@sha256:fb16b180bd9727600067e16fcd6a6de43fb4db1baf4298ef20b4dbdf6bfa5a0e`
 - vLLM: `0.1.dev19262+gb6bbf29dd.d20260727`
 - Hardware: NVIDIA B200, SM100; torch `2.13.0+cu130`, CUDA 13.0
-- Exact MoE shape: 896 routed experts, top-k 16, `3584 -> 3072 -> 3584`, 2 tokens
-- Loaded tensors: 8,064 (`U8=2,688`, `F8_E4M3=2,688`, `F32=2,688`); all 896 experts
+- Complete path: FP32 router + correction bias, `7168 -> 3584` latent down,
+  896 routed experts with real top-k 16 and `3584 -> 3072 -> 3584`, routed
+  RMSNorm + `3584 -> 7168` up, and 2 shared experts (`7168 -> 6144 -> 7168`)
+- Loaded source tensors: 8,072 = 8 nonexpert block tensors + 8,064 routed-expert
+  quant tensors; all 896 experts
 - SiTU: beta `4.0`, linear beta `25.0`
 - Backend: `MARLIN` / `MarlinExperts`
-- Observed operators: `_moe_C::moe_wna16_marlin_gemm` (2 calls), Marlin CUDA
-  kernel, `_C::situ_and_mul`, `vllm::situ_and_mul_kernel`, routing alignment,
-  and MoE sum
-- Output: shape `[2, 3584]`, finite and nonzero
+- Observed operators: `vllm::moe_forward_shared`,
+  `_moe_C::moe_wna16_marlin_gemm`, `_moe_C::grouped_topk`,
+  `_C::situ_and_mul`, `vllm_ir::rms_norm`, routing alignment, and MoE sum
+- Router logits: `[2, 896]`; selected IDs `[2, 16]`; 16 unique in-range
+  experts per token; finite normalized weights
+- Both direct and real model-class-loader outputs: `[2, 7168]`, finite and
+  nonzero; sampled parameter fingerprints matched exactly and outputs were
+  bit-exact (`max_abs_difference=0`)
+- Complete-block validation run cost: `$0.341178`; all attempts including the
+  externally canceled run: `$3.892933 < $4.5`
+
+This verifies the real K3 outer/inner `load_weights` mapping and generic
+post-load traversal on a reduced one-block wrapper. `DefaultModelLoader`
+index/file traversal was not exercised, and the full model was not constructed.
 
 **SGLang runtime was not executed.** A zero-cost gate against the official
 `lmsysorg/sglang:kimi-k3` image (linux/amd64 digest
@@ -71,9 +88,10 @@ FLOAT tensor-group MoE path for `input_activations: null`. The gate therefore
 returned `BLOCKED / DO_NOT_RUN_GPU` (`20260727T221943Z`) before weight download
 or GPU allocation.
 
-Not verified: the full 93-layer / 2.8T model, KDA/MLA/vision integration,
-all 96 shards loaded together, end-to-end token generation, serving quality,
-or SGLang load/forward/kernel dispatch.
+Not verified: the full 93-layer / 2.8T model, all 96 shards resident together,
+`DefaultModelLoader` index/file traversal, KDA/MLA/vision integration, TP16,
+end-to-end token generation, serving quality, or SGLang load/forward/kernel
+dispatch.
 
 ## License
 

nvfp4_conversion_manifest.json

@@ -19,14 +19,26 @@
   "tensor_bytes": 1645946964992,
   "lossless_over_span_policy": "fail; never silently requantize",
   "runtime_validation": {
-    "level": "vllm_one_layer_routed_moe",
+    "level": "vllm_complete_stable_latent_moe_reduced_model_class_loader",
     "vllm_verified": true,
-    "vllm_run_id": "20260727T220141Z",
+    "vllm_run_id": "20260727T234215Z",
+    "vllm_routed_expert_core_run_id": "20260727T220141Z",
     "vllm_image_amd64_digest": "sha256:fb16b180bd9727600067e16fcd6a6de43fb4db1baf4298ef20b4dbdf6bfa5a0e",
+    "complete_stable_latent_moe_verified": true,
+    "real_k3_load_weights_mapping_verified": true,
+    "generic_post_load_traversal_verified": true,
+    "default_model_loader_file_traversal_verified": false,
+    "loader_chain": [
+      "KimiK3ForConditionalGeneration.load_weights",
+      "AutoWeightsLoader",
+      "KimiLinearForCausalLM.load_weights",
+      "KimiLinearModel.load_weights"
+    ],
     "sglang_verified": false,
     "sglang_static_gate": "BLOCKED",
     "sglang_static_run_id": "20260727T221943Z",
     "full_model_load_verified": false,
-    "full_generation_verified": false
+    "full_generation_verified": false,
+    "tp16_verified": false
   }
 }