Add ReplayServe Frontier vLLM alignment report

traces/fixtures/coder_100/manifest.json

@@ -0,0 +1,48 @@
+{
+  "adapter_semantics": {
+    "block_token_counts": "full blocks use block_size tokens; final partial block uses input_length % block_size, or block_size when zero",
+    "chat_id": "session_id",
+    "hash_ids": "block_hash_ids joined by |",
+    "input_length": "num_prefill_tokens",
+    "output_length": "num_decode_tokens",
+    "timestamp": "arrived_at"
+  },
+  "block_size": 16,
+  "csv_fields": [
+    "arrived_at",
+    "num_prefill_tokens",
+    "num_decode_tokens",
+    "session_id",
+    "block_hash_ids"
+  ],
+  "fail_on_overflow": true,
+  "first_timestamp": 0.0,
+  "fixture_name": "coder_100",
+  "frontier_csv": "traces/fixtures/coder_100/frontier.csv",
+  "generated_by": "tools/qwen_to_frontier.py",
+  "input_jsonl": "/home/gahow/phd/qwen-bailian-usagetraces-anon/qwen_coder_blksz_16.jsonl",
+  "last_timestamp": 22.623,
+  "limit": 100,
+  "max_input_length": 17972,
+  "max_output_length": 7279,
+  "max_tokens": 32768,
+  "max_total_tokens": 18985,
+  "overflow_count": 0,
+  "partial_final_block_rows": 91,
+  "row_count": 100,
+  "sidecar_fields": [
+    "request_id",
+    "chat_id",
+    "parent_chat_id",
+    "turn",
+    "type",
+    "timestamp",
+    "input_length",
+    "output_length",
+    "hash_ids",
+    "block_token_counts"
+  ],
+  "sidecar_jsonl": "traces/fixtures/coder_100/sidecar.jsonl",
+  "source_jsonl": "traces/fixtures/coder_100/source.jsonl",
+  "timestamp_monotonic": true
+}

traces/fixtures/coder_2000/manifest.json

@@ -0,0 +1,48 @@
+{
+  "adapter_semantics": {
+    "block_token_counts": "full blocks use block_size tokens; final partial block uses input_length % block_size, or block_size when zero",
+    "chat_id": "session_id",
+    "hash_ids": "block_hash_ids joined by |",
+    "input_length": "num_prefill_tokens",
+    "output_length": "num_decode_tokens",
+    "timestamp": "arrived_at"
+  },
+  "block_size": 16,
+  "csv_fields": [
+    "arrived_at",
+    "num_prefill_tokens",
+    "num_decode_tokens",
+    "session_id",
+    "block_hash_ids"
+  ],
+  "fail_on_overflow": true,
+  "first_timestamp": 0.0,
+  "fixture_name": "coder_2000",
+  "frontier_csv": "traces/fixtures/coder_2000/frontier.csv",
+  "generated_by": "tools/qwen_to_frontier.py",
+  "input_jsonl": "/home/gahow/phd/qwen-bailian-usagetraces-anon/qwen_coder_blksz_16.jsonl",
+  "last_timestamp": 451.684,
+  "limit": 2000,
+  "max_input_length": 17972,
+  "max_output_length": 10768,
+  "max_tokens": 32768,
+  "max_total_tokens": 21318,
+  "overflow_count": 0,
+  "partial_final_block_rows": 1879,
+  "row_count": 2000,
+  "sidecar_fields": [
+    "request_id",
+    "chat_id",
+    "parent_chat_id",
+    "turn",
+    "type",
+    "timestamp",
+    "input_length",
+    "output_length",
+    "hash_ids",
+    "block_token_counts"
+  ],
+  "sidecar_jsonl": "traces/fixtures/coder_2000/sidecar.jsonl",
+  "source_jsonl": "traces/fixtures/coder_2000/source.jsonl",
+  "timestamp_monotonic": true
+}

traces/fixtures/coder_200_ts0667/manifest.json

@@ -0,0 +1,49 @@
+{
+  "adapter_semantics": {
+    "block_token_counts": "full blocks use block_size tokens; final partial block uses input_length % block_size, or block_size when zero",
+    "chat_id": "session_id",
+    "hash_ids": "block_hash_ids joined by |",
+    "input_length": "num_prefill_tokens",
+    "output_length": "num_decode_tokens",
+    "timestamp": "arrived_at"
+  },
+  "block_size": 16,
+  "csv_fields": [
+    "arrived_at",
+    "num_prefill_tokens",
+    "num_decode_tokens",
+    "session_id",
+    "block_hash_ids"
+  ],
+  "fail_on_overflow": true,
+  "first_timestamp": 0.0,
+  "fixture_name": "coder_200_ts0667",
+  "frontier_csv": "/home/gahow/phd/replayserve/traces/fixtures/coder_200_ts0667/frontier.csv",
+  "generated_by": "tools/qwen_to_frontier.py",
+  "input_jsonl": "/home/gahow/phd/qwen-bailian-usagetraces-anon/qwen_coder_blksz_16.jsonl",
+  "last_timestamp": 30.711333333333332,
+  "limit": 200,
+  "max_input_length": 17972,
+  "max_output_length": 7279,
+  "max_tokens": 32768,
+  "max_total_tokens": 18985,
+  "overflow_count": 0,
+  "partial_final_block_rows": 182,
+  "row_count": 200,
+  "sidecar_fields": [
+    "request_id",
+    "chat_id",
+    "parent_chat_id",
+    "turn",
+    "type",
+    "timestamp",
+    "input_length",
+    "output_length",
+    "hash_ids",
+    "block_token_counts"
+  ],
+  "sidecar_jsonl": "/home/gahow/phd/replayserve/traces/fixtures/coder_200_ts0667/sidecar.jsonl",
+  "source_jsonl": "/home/gahow/phd/replayserve/traces/fixtures/coder_200_ts0667/source.jsonl",
+  "timestamp_monotonic": true,
+  "timestamp_scale": 0.6666666666666666
+}

traces/fixtures/coder_200_ts2/manifest.json

@@ -0,0 +1,49 @@
+{
+  "adapter_semantics": {
+    "block_token_counts": "full blocks use block_size tokens; final partial block uses input_length % block_size, or block_size when zero",
+    "chat_id": "session_id",
+    "hash_ids": "block_hash_ids joined by |",
+    "input_length": "num_prefill_tokens",
+    "output_length": "num_decode_tokens",
+    "timestamp": "arrived_at"
+  },
+  "block_size": 16,
+  "csv_fields": [
+    "arrived_at",
+    "num_prefill_tokens",
+    "num_decode_tokens",
+    "session_id",
+    "block_hash_ids"
+  ],
+  "fail_on_overflow": true,
+  "first_timestamp": 0.0,
+  "fixture_name": "coder_200_ts2",
+  "frontier_csv": "/home/gahow/phd/replayserve/traces/fixtures/coder_200_ts2/frontier.csv",
+  "generated_by": "tools/qwen_to_frontier.py",
+  "input_jsonl": "/home/gahow/phd/qwen-bailian-usagetraces-anon/qwen_coder_blksz_16.jsonl",
+  "last_timestamp": 92.134,
+  "limit": 200,
+  "max_input_length": 17972,
+  "max_output_length": 7279,
+  "max_tokens": 32768,
+  "max_total_tokens": 18985,
+  "overflow_count": 0,
+  "partial_final_block_rows": 182,
+  "row_count": 200,
+  "sidecar_fields": [
+    "request_id",
+    "chat_id",
+    "parent_chat_id",
+    "turn",
+    "type",
+    "timestamp",
+    "input_length",
+    "output_length",
+    "hash_ids",
+    "block_token_counts"
+  ],
+  "sidecar_jsonl": "/home/gahow/phd/replayserve/traces/fixtures/coder_200_ts2/sidecar.jsonl",
+  "source_jsonl": "/home/gahow/phd/replayserve/traces/fixtures/coder_200_ts2/source.jsonl",
+  "timestamp_monotonic": true,
+  "timestamp_scale": 2.0
+}

traces/fixtures/coder_200_ts3/manifest.json

@@ -0,0 +1,49 @@
+{
+  "adapter_semantics": {
+    "block_token_counts": "full blocks use block_size tokens; final partial block uses input_length % block_size, or block_size when zero",
+    "chat_id": "session_id",
+    "hash_ids": "block_hash_ids joined by |",
+    "input_length": "num_prefill_tokens",
+    "output_length": "num_decode_tokens",
+    "timestamp": "arrived_at"
+  },
+  "block_size": 16,
+  "csv_fields": [
+    "arrived_at",
+    "num_prefill_tokens",
+    "num_decode_tokens",
+    "session_id",
+    "block_hash_ids"
+  ],
+  "fail_on_overflow": true,
+  "first_timestamp": 0.0,
+  "fixture_name": "coder_200_ts3",
+  "frontier_csv": "/home/gahow/phd/replayserve/traces/fixtures/coder_200_ts3/frontier.csv",
+  "generated_by": "tools/qwen_to_frontier.py",
+  "input_jsonl": "/home/gahow/phd/qwen-bailian-usagetraces-anon/qwen_coder_blksz_16.jsonl",
+  "last_timestamp": 138.201,
+  "limit": 200,
+  "max_input_length": 17972,
+  "max_output_length": 7279,
+  "max_tokens": 32768,
+  "max_total_tokens": 18985,
+  "overflow_count": 0,
+  "partial_final_block_rows": 182,
+  "row_count": 200,
+  "sidecar_fields": [
+    "request_id",
+    "chat_id",
+    "parent_chat_id",
+    "turn",
+    "type",
+    "timestamp",
+    "input_length",
+    "output_length",
+    "hash_ids",
+    "block_token_counts"
+  ],
+  "sidecar_jsonl": "/home/gahow/phd/replayserve/traces/fixtures/coder_200_ts3/sidecar.jsonl",
+  "source_jsonl": "/home/gahow/phd/replayserve/traces/fixtures/coder_200_ts3/source.jsonl",
+  "timestamp_monotonic": true,
+  "timestamp_scale": 3.0
+}

traces/fixtures/coder_500/manifest.json

@@ -0,0 +1,48 @@
+{
+  "adapter_semantics": {
+    "block_token_counts": "full blocks use block_size tokens; final partial block uses input_length % block_size, or block_size when zero",
+    "chat_id": "session_id",
+    "hash_ids": "block_hash_ids joined by |",
+    "input_length": "num_prefill_tokens",
+    "output_length": "num_decode_tokens",
+    "timestamp": "arrived_at"
+  },
+  "block_size": 16,
+  "csv_fields": [
+    "arrived_at",
+    "num_prefill_tokens",
+    "num_decode_tokens",
+    "session_id",
+    "block_hash_ids"
+  ],
+  "fail_on_overflow": true,
+  "first_timestamp": 0.0,
+  "fixture_name": "coder_500",
+  "frontier_csv": "/home/gahow/phd/replayserve/traces/fixtures/coder_500/frontier.csv",
+  "generated_by": "tools/qwen_to_frontier.py",
+  "input_jsonl": "/home/gahow/phd/qwen-bailian-usagetraces-anon/qwen_coder_blksz_16.jsonl",
+  "last_timestamp": 109.466,
+  "limit": 500,
+  "max_input_length": 17972,
+  "max_output_length": 8533,
+  "max_tokens": 32768,
+  "max_total_tokens": 21318,
+  "overflow_count": 0,
+  "partial_final_block_rows": 466,
+  "row_count": 500,
+  "sidecar_fields": [
+    "request_id",
+    "chat_id",
+    "parent_chat_id",
+    "turn",
+    "type",
+    "timestamp",
+    "input_length",
+    "output_length",
+    "hash_ids",
+    "block_token_counts"
+  ],
+  "sidecar_jsonl": "/home/gahow/phd/replayserve/traces/fixtures/coder_500/sidecar.jsonl",
+  "source_jsonl": "/home/gahow/phd/replayserve/traces/fixtures/coder_500/source.jsonl",
+  "timestamp_monotonic": true
+}