gspark-etri · Oct 23, 2026 · Oct 23, 2026
diff --git a/opt_prime/examples/pd/http_matrix/.research/events.jsonl b/opt_prime/examples/pd/http_matrix/.research/events.jsonl
@@ -1,2 +1,5 @@
 {"id": "b61f99ae005a4258aa7f44d8edeca28d", "ts": "2026-10-23T18:08:44+09:00", "task": "Four-model HTTP matrix (aicomp #211)", "result": "All4 GPU models pass HTTP concurrency4/8, cancel/disconnect/drain/reuse checks. No-cacheBF16 and warm-cacheFP32 each48/48 concurrent outputs exact. Warm-cacheBF16 has31/48 raw equality; actualQwenHTTP tie explains observed branch. Warm-state cancellation isolates KONI cold-cache difference.", "next": "Publish GPUHTTP evidence; continue ATOM HTTP and RNGD routes. Preserve numerical/quality and true-overlap limitations.", "state": "active", "done": false, "blocker": "", "metrics": {}, "params": {"models": "4", "slots": "4", "concurrency": "4,8", "conditions": "bf16_no_cache,bf16_cache,fp32_cache"}, "artifacts": ["evidence/summary.json"], "experiments": ["experiments/2026-10-23-http-matrix211.md"], "labels": ["benchmark"], "review": true, "todos": [], "note": "", "agent": "codex", "host": "GPU host", "branch": "main", "commit": "351d39d-dirty"}
 {"id": "3563031e43c8478e951fff82f81bfe94", "ts": "2026-10-23T18:38:18+09:00", "task": "Four-model serving matrix (aicomp #201)", "result": "ATOM HTTP: all four models pass 128/2048/8192-token lifecycle checks; cache-off concurrent48/48 exact. Both Qwen device/host cache cases pass12/12 each. SIGPIPE candidate suppresses native disconnect backtraces6 to0 with unchanged outputs;14 unit/integration tests pass.", "next": "Publish ATOM HTTP matrix and SIGPIPE fix; continue missing RNGD and hybrid-state routes.", "state": "active", "done": false, "blocker": "", "metrics": {}, "params": {"backend": "atom", "input_tokens": "128,2048,8192", "output_tokens": "32", "hardware_batch": "1"}, "artifacts": ["evidence/atom-http-qwen3-4b-host-fixed.json"], "experiments": ["experiments/2026-10-23-atom-http211.md"], "labels": ["experiment", "bug"], "review": false, "todos": [], "note": "", "agent": "codex", "host": "RNGD+ATOM host", "branch": "exp/211-atom-http", "commit": "working candidate"}
+{"id": "4c7935b757264687b1310fbe1ec6399a", "ts": "2026-10-23T21:26:38+09:00", "task": "Tokenizer EOS in batched serving (aicomp #229)", "result": "Production factory union of generation-config/tokenizer EOS fixes real KONI HTTP turn end: baseline length, fixed stop, ignore_eos length, streaming stop, reuse stop. Baseline factory3fail/3pass ->22related tests pass. Preserved failed initial SSE checker log.", "next": "Publish scoped serving fix; verify NPU HTTP and retain long RNGD semantic validation.", "state": "active", "done": false, "blocker": "", "metrics": {}, "params": {"model": "KONI-8B", "backend": "gpu", "max_tokens": "8"}, "artifacts": [{"path": "analysis/serving-matrix-201/eos229-koni-http-final.json", "size": 5067, "sha256": "d5be9a4a52a6485f"}], "experiments": ["experiments/2026-10-23-serving-eos229.md"], "labels": ["bug"], "review": true, "todos": [], "note": "", "agent": "codex", "host": "xeon-max", "branch": "main", "commit": "351d39d-dirty"}
+{"id": "e4993823527144b5a14e6441b1cd5c01", "ts": "2026-10-23T21:29:56+09:00", "task": "Tokenizer EOS in batched serving (aicomp #229)", "result": "Published production EOS fix and real KONI HTTP evidence in draft PR230 (e5fa087). Final factory/streaming/sampling/batched suite22passed; hardware checker5/5 cases passed; changed files sensitive-clean,4unchanged baseline findings in this branch.", "next": "Verify same HTTP factory on NPU; continue full four-model long semantic and heterogeneous PD validation.", "state": "active", "done": false, "blocker": "", "metrics": {}, "params": {"backend": "gpu"}, "artifacts": [{"path": "analysis/serving-matrix-201/eos229-koni-http-final.json", "size": 5067, "sha256": "d5be9a4a52a6485f"}], "experiments": ["experiments/2026-10-23-serving-eos229.md"], "labels": ["bug"], "review": true, "todos": [], "note": "", "agent": "codex", "host": "xeon-max", "branch": "main", "commit": "351d39d-dirty"}
+{"id": "328b8349e9974a059ddc7e1a8a485e2c", "ts": "2026-10-23T21:32:23+09:00", "task": "Tokenizer EOS in batched serving (aicomp #229)", "result": "Real ATOM KONI HTTP also passes5/5 baseline/fixed/ignore/stream/reuse checks using same production factory: config-only length vs union stop. GPU+ATOM now10/10 expected outcomes; no SDK/artifact rebuild.", "next": "Update PR230 with NPU evidence; finish KONI medium-context RNGD handoff and broader PD work.", "state": "active", "done": false, "blocker": "", "metrics": {}, "params": {"backend": "atom", "kv_blocks": "1"}, "artifacts": [{"path": "analysis/serving-matrix-201/eos229-koni-atom-http.json", "size": 5199, "sha256": "4735255db379ff00"}], "experiments": ["experiments/2026-10-23-serving-eos229.md"], "labels": ["bug"], "review": true, "todos": [], "note": "", "agent": "codex", "host": "xeon-max", "branch": "main", "commit": "351d39d-dirty"}
diff --git a/opt_prime/examples/pd/http_matrix/STATUS.md b/opt_prime/examples/pd/http_matrix/STATUS.md
@@ -1,3 +1,7 @@
 # HTTP model matrix
 
 State: review; full goal remains active. GPU evidence remains as recorded. ATOM four-model cache-off lifecycle passes with48/48 concurrent equality; both Qwen device/host cache cases pass12/12 each. SIGPIPE fix tracked separately in #214. Remaining: RNGD routes, hybrid-state restoration, real transfer overlap and broader semantic testing.
+
+## Production EOS correction (#229)
+
+The common serve_batched factory now unions model generation EOS and tokenizer turn-end EOS. KONI config128001/tokenizer128009 previously continued into role delimiters; real GPU HTTP negative control ends length, fixed/stream/reuse end stop, ignore_eos remains length.22related CPU tests pass after3failed factory regressions. GPU and ATOM hardware both pass5/5 EOS/override/stream/reuse checks; NPU uses existing B1/context9216/k1 artifact. See serving-eos229 record/evidence229.
diff --git a/opt_prime/examples/pd/http_matrix/evidence229/koni-atom-http.json b/opt_prime/examples/pd/http_matrix/evidence229/koni-atom-http.json
@@ -0,0 +1,154 @@
+[
+  {
+    "case": "baseline",
+    "eos_ids": [
+      128001
+    ],
+    "response": {
+      "id": "baseline",
+      "object": "text_completion",
+      "created": 1792758717,
+      "model": "KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024",
+      "choices": [
+        {
+          "index": 0,
+          "text": "Parisuser\n\nWhat is",
+          "token_ids": [
+            60704,
+            128009,
+            128006,
+            882,
+            128007,
+            271,
+            3923,
+            374
+          ],
+          "finish_reason": "length"
+        }
+      ],
+      "usage": {
+        "prompt_tokens": 138,
+        "completion_tokens": 8,
+        "total_tokens": 146
+      }
+    },
+    "raw": "{\"id\": \"baseline\", \"object\": \"text_completion\", \"created\": 1792758717, \"model\": \"KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024\", \"choices\": [{\"index\": 0, \"text\": \"Parisuser\\n\\nWhat is\", \"token_ids\": [60704, 128009, 128006, 882, 128007, 271, 3923, 374], \"finish_reason\": \"length\"}], \"usage\": {\"prompt_tokens\": 138, \"completion_tokens\": 8, \"total_tokens\": 146}}"
+  },
+  {
+    "case": "fixed",
+    "eos_ids": [
+      128001,
+      128009
+    ],
+    "response": {
+      "id": "fixed",
+      "object": "text_completion",
+      "created": 1792758717,
+      "model": "KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024",
+      "choices": [
+        {
+          "index": 0,
+          "text": "Paris",
+          "token_ids": [
+            60704,
+            128009
+          ],
+          "finish_reason": "stop"
+        }
+      ],
+      "usage": {
+        "prompt_tokens": 138,
+        "completion_tokens": 2,
+        "total_tokens": 140
+      }
+    },
+    "raw": "{\"id\": \"fixed\", \"object\": \"text_completion\", \"created\": 1792758717, \"model\": \"KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024\", \"choices\": [{\"index\": 0, \"text\": \"Paris\", \"token_ids\": [60704, 128009], \"finish_reason\": \"stop\"}], \"usage\": {\"prompt_tokens\": 138, \"completion_tokens\": 2, \"total_tokens\": 140}}"
+  },
+  {
+    "case": "ignore",
+    "eos_ids": [
+      128001,
+      128009
+    ],
+    "response": {
+      "id": "ignore",
+      "object": "text_completion",
+      "created": 1792758718,
+      "model": "KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024",
+      "choices": [
+        {
+          "index": 0,
+          "text": "Parisuser\n\nWhat is",
+          "token_ids": [
+            60704,
+            128009,
+            128006,
+            882,
+            128007,
+            271,
+            3923,
+            374
+          ],
+          "finish_reason": "length"
+        }
+      ],
+      "usage": {
+        "prompt_tokens": 138,
+        "completion_tokens": 8,
+        "total_tokens": 146
+      }
+    },
+    "raw": "{\"id\": \"ignore\", \"object\": \"text_completion\", \"created\": 1792758718, \"model\": \"KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024\", \"choices\": [{\"index\": 0, \"text\": \"Parisuser\\n\\nWhat is\", \"token_ids\": [60704, 128009, 128006, 882, 128007, 271, 3923, 374], \"finish_reason\": \"length\"}], \"usage\": {\"prompt_tokens\": 138, \"completion_tokens\": 8, \"total_tokens\": 146}}"
+  },
+  {
+    "case": "stream",
+    "eos_ids": [
+      128001,
+      128009
+    ],
+    "response": {
+      "id": "stream",
+      "object": "text_completion",
+      "created": 1792758718,
+      "model": "KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024",
+      "choices": [
+        {
+          "index": 0,
+          "text": "",
+          "finish_reason": "stop"
+        }
+      ]
+    },
+    "raw": "data: {\"id\": \"stream\", \"object\": \"text_completion\", \"created\": 1792758718, \"model\": \"KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024\", \"choices\": [{\"index\": 0, \"text\": \"Paris\", \"finish_reason\": null}]}\n\ndata: {\"id\": \"stream\", \"object\": \"text_completion\", \"created\": 1792758718, \"model\": \"KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024\", \"choices\": [{\"index\": 0, \"text\": \"\", \"finish_reason\": \"stop\"}]}\n\ndata: {\"id\": \"stream\", \"object\": \"text_completion\", \"created\": 1792758718, \"model\": \"KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024\", \"choices\": [], \"usage\": {\"prompt_tokens\": 138, \"completion_tokens\": 2, \"total_tokens\": 140}}\n\ndata: [DONE]\n\n"
+  },
+  {
+    "case": "reuse",
+    "eos_ids": [
+      128001,
+      128009
+    ],
+    "response": {
+      "id": "reuse",
+      "object": "text_completion",
+      "created": 1792758718,
+      "model": "KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024",
+      "choices": [
+        {
+          "index": 0,
+          "text": "Paris",
+          "token_ids": [
+            60704,
+            128009
+          ],
+          "finish_reason": "stop"
+        }
+      ],
+      "usage": {
+        "prompt_tokens": 138,
+        "completion_tokens": 2,
+        "total_tokens": 140
+      }
+    },
+    "raw": "{\"id\": \"reuse\", \"object\": \"text_completion\", \"created\": 1792758718, \"model\": \"KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024\", \"choices\": [{\"index\": 0, \"text\": \"Paris\", \"token_ids\": [60704, 128009], \"finish_reason\": \"stop\"}], \"usage\": {\"prompt_tokens\": 138, \"completion_tokens\": 2, \"total_tokens\": 140}}"
+  }
+]
diff --git a/opt_prime/examples/pd/http_matrix/evidence229/koni-capital-fixture.json b/opt_prime/examples/pd/http_matrix/evidence229/koni-capital-fixture.json
@@ -0,0 +1,152 @@
+{
+  "eos_ids": [
+    128001,
+    128009
+  ],
+  "cases": [
+    {
+      "case": "capital-0",
+      "ids": [
+        128000,
+        128006,
+        9125,
+        128007,
+        271,
+        2675,
+        527,
+        735,
+        715,
+        40,
+        11,
+        459,
+        15592,
+        18328,
+        16572,
+        3196,
+        389,
+        445,
+        4355,
+        4940,
+        18,
+        13,
+        16,
+        323,
+        3549,
+        555,
+        735,
+        3931,
+        40,
+        311,
+        387,
+        11190,
+        323,
+        10978,
+        13,
+        4718,
+        6677,
+        45395,
+        264,
+        7029,
+        2134,
+        315,
+        13650,
+        11,
+        10923,
+        499,
+        311,
+        16988,
+        304,
+        67749,
+        21633,
+        323,
+        3493,
+        6492,
+        389,
+        6485,
+        15223,
+        13,
+        21883,
+        374,
+        459,
+        7754,
+        430,
+        16964,
+        264,
+        3465,
+        13,
+        9842,
+        264,
+        2077,
+        430,
+        36001,
+        45695,
+        279,
+        1715,
+        13,
+        1442,
+        499,
+        1541,
+        956,
+        1440,
+        279,
+        4320,
+        11,
+        1120,
+        2019,
+        430,
+        499,
+        1541,
+        956,
+        1440,
+        627,
+        38766,
+        1303,
+        33025,
+        2696,
+        25,
+        5887,
+        220,
+        2366,
+        19,
+        198,
+        15724,
+        2696,
+        25,
+        220,
+        1544,
+        5033,
+        220,
+        2366,
+        19,
+        271,
+        128009,
+        128006,
+        882,
+        128007,
+        271,
+        3923,
+        374,
+        279,
+        6864,
+        315,
+        9822,
+        30,
+        18321,
+        449,
+        1193,
+        279,
+        3363,
+        836,
+        13,
+        128009,
+        128006,
+        42,
+        715,
+        40,
+        128007,
+        271
+      ],
+      "question": "What is the capital of France? Reply with only the city name."
+    }
+  ]
+}