tzhouamandClaude Opus 5
9264ff81ab
The packaging commit shipped the code and a summary of the numbers. It left out
everything the numbers are measured *against*, which is most of what makes them
checkable.
Added:
baselines/ llama.cpp runs (thread sweeps, NUMA sweeps, the
interleaved A/B passes behind the headline decode
figure) and the quality references: each build
against its own bf16 over 12 greedy prompts.
benchmarks/.../results/ 102 artifacts backing the published figures, each
with a provenance block naming the model,
quantization, thread set and build SHAs.
docs/engines/ the engine analyses -- llama.cpp, ExecuTorch, MNN,
ncnn, vLLM, vLLM-Omni -- and the cross-engine and
device-simulation comparisons.
docs/analysis/ the full study documents the summaries distil.
docs/edge/comparisons.md where this fork sits against llama.cpp and why:
decode is llama.cpp's, prefill is ours by ~2x, and
since neither engine exceeds 39% of the measured
222 GB/s ceiling the decode gap is the execution
model rather than the kernels.
docs/edge/environment.md pins and machine, and the correction below.
On "the modified vllm": there isn't one, and the doc says so plainly because it
is the obvious assumption. The vLLM checkout is clean upstream (0 commits
ahead, 0 uncommitted) and the installed wheel is stock 0.28.0+cpu. This fork
changes vLLM's CPU *behaviour* through vLLM's own extension points at import
time -- three CPU patches in vllm_omni/patch.py, the quantization-config
registry, the IR op registry, platform hooks -- specifically so the changes
survive a wheel upgrade rather than being lost on it. One of those patches is
why "KV sizing is not a memory lever" looked true for months: CpuPlatform
overwrote kv_cache_memory_bytes unconditionally, so the setting had no effect.
There is no patch series to apply; pin the version and let patch.py do the rest.
.gitignore gains explicit exceptions: upstream's blanket `*.json` and `results/`
rules were silently eating the measurement artifacts, which in this fork are the
substance rather than build output. Binary captures stay ignored.
No vLLM or llama.cpp source is redistributed -- only output produced with them.
NOTICE records both.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01L1ax5wYLA6XbqEL1i8L9gZ
273 lines
8.0 KiB
JSON
273 lines
8.0 KiB
JSON
[
|
|
{
|
|
"build_commit": "e71b80510",
|
|
"build_number": 10849,
|
|
"cpu_info": "Intel(R) Xeon(R) Platinum 8480C",
|
|
"gpu_info": "",
|
|
"backends": "CPU",
|
|
"model_filename": "/data/zhoutaichang/.cache/huggingface/hub/models--XHToken--Spark-X2.5-1.7B-GGUF/snapshots/23e1fcac55e7dd71e4c12a23723cc228ba0e5e85/Spark-X2.5-1.7B.gguf",
|
|
"model_type": "spark2_5 1.7B BF16",
|
|
"model_size": 3415547904,
|
|
"model_n_params": 1707657216,
|
|
"n_batch": 2048,
|
|
"n_ubatch": 512,
|
|
"n_threads": 8,
|
|
"cpu_mask": "0x0",
|
|
"cpu_strict": false,
|
|
"poll": 50,
|
|
"type_k": "f16",
|
|
"type_v": "f16",
|
|
"n_gpu_layers": -1,
|
|
"n_cpu_moe": 0,
|
|
"split_mode": "layer",
|
|
"main_gpu": 0,
|
|
"no_kv_offload": false,
|
|
"flash_attn": -1,
|
|
"devices": "auto",
|
|
"tensor_split": "0.00",
|
|
"tensor_buft_overrides": "none",
|
|
"load_mode": "auto",
|
|
"lazy_mode": "auto",
|
|
"embeddings": false,
|
|
"no_op_offload": 0,
|
|
"no_host": false,
|
|
"fit_target": 0,
|
|
"fit_min_ctx": 0,
|
|
"n_prompt": 512,
|
|
"n_gen": 0,
|
|
"n_depth": 0,
|
|
"test_time": "2026-09-11T06:28:17Z",
|
|
"avg_ns": 2946090115,
|
|
"stddev_ns": 19481720,
|
|
"avg_ts": 173.795716,
|
|
"stddev_ts": 1.144798,
|
|
"samples_ns": [ 2976783425, 2943842928, 2936842142, 2948762947, 2924219135 ],
|
|
"samples_ts": [ 171.998, 173.922, 174.337, 173.632, 175.089 ]
|
|
},
|
|
{
|
|
"build_commit": "e71b80510",
|
|
"build_number": 10849,
|
|
"cpu_info": "Intel(R) Xeon(R) Platinum 8480C",
|
|
"gpu_info": "",
|
|
"backends": "CPU",
|
|
"model_filename": "/data/zhoutaichang/.cache/huggingface/hub/models--XHToken--Spark-X2.5-1.7B-GGUF/snapshots/23e1fcac55e7dd71e4c12a23723cc228ba0e5e85/Spark-X2.5-1.7B.gguf",
|
|
"model_type": "spark2_5 1.7B BF16",
|
|
"model_size": 3415547904,
|
|
"model_n_params": 1707657216,
|
|
"n_batch": 2048,
|
|
"n_ubatch": 512,
|
|
"n_threads": 8,
|
|
"cpu_mask": "0x0",
|
|
"cpu_strict": false,
|
|
"poll": 50,
|
|
"type_k": "f16",
|
|
"type_v": "f16",
|
|
"n_gpu_layers": -1,
|
|
"n_cpu_moe": 0,
|
|
"split_mode": "layer",
|
|
"main_gpu": 0,
|
|
"no_kv_offload": false,
|
|
"flash_attn": -1,
|
|
"devices": "auto",
|
|
"tensor_split": "0.00",
|
|
"tensor_buft_overrides": "none",
|
|
"load_mode": "auto",
|
|
"lazy_mode": "auto",
|
|
"embeddings": false,
|
|
"no_op_offload": 0,
|
|
"no_host": false,
|
|
"fit_target": 0,
|
|
"fit_min_ctx": 0,
|
|
"n_prompt": 0,
|
|
"n_gen": 128,
|
|
"n_depth": 0,
|
|
"test_time": "2026-09-11T06:28:34Z",
|
|
"avg_ns": 7926507628,
|
|
"stddev_ns": 166210109,
|
|
"avg_ts": 16.153997,
|
|
"stddev_ts": 0.336782,
|
|
"samples_ns": [ 7746359669, 7836100448, 8141583693, 8059318007, 7849176324 ],
|
|
"samples_ts": [ 16.5239, 16.3347, 15.7218, 15.8822, 16.3074 ]
|
|
},
|
|
{
|
|
"build_commit": "e71b80510",
|
|
"build_number": 10849,
|
|
"cpu_info": "Intel(R) Xeon(R) Platinum 8480C",
|
|
"gpu_info": "",
|
|
"backends": "CPU",
|
|
"model_filename": "/data/zhoutaichang/.cache/huggingface/hub/models--XHToken--Spark-X2.5-1.7B-GGUF/snapshots/23e1fcac55e7dd71e4c12a23723cc228ba0e5e85/Spark-X2.5-1.7B-Q8_0.gguf",
|
|
"model_type": "spark2_5 1.7B Q8_0",
|
|
"model_size": 1814728704,
|
|
"model_n_params": 1707657216,
|
|
"n_batch": 2048,
|
|
"n_ubatch": 512,
|
|
"n_threads": 8,
|
|
"cpu_mask": "0x0",
|
|
"cpu_strict": false,
|
|
"poll": 50,
|
|
"type_k": "f16",
|
|
"type_v": "f16",
|
|
"n_gpu_layers": -1,
|
|
"n_cpu_moe": 0,
|
|
"split_mode": "layer",
|
|
"main_gpu": 0,
|
|
"no_kv_offload": false,
|
|
"flash_attn": -1,
|
|
"devices": "auto",
|
|
"tensor_split": "0.00",
|
|
"tensor_buft_overrides": "none",
|
|
"load_mode": "auto",
|
|
"lazy_mode": "auto",
|
|
"embeddings": false,
|
|
"no_op_offload": 0,
|
|
"no_host": false,
|
|
"fit_target": 0,
|
|
"fit_min_ctx": 0,
|
|
"n_prompt": 512,
|
|
"n_gen": 0,
|
|
"n_depth": 0,
|
|
"test_time": "2026-09-11T06:29:15Z",
|
|
"avg_ns": 1044627273,
|
|
"stddev_ns": 8668625,
|
|
"avg_ts": 490.153690,
|
|
"stddev_ts": 4.025039,
|
|
"samples_ns": [ 1040367711, 1059967868, 1042470115, 1039018745, 1041311927 ],
|
|
"samples_ts": [ 492.134, 483.034, 491.141, 492.773, 491.687 ]
|
|
},
|
|
{
|
|
"build_commit": "e71b80510",
|
|
"build_number": 10849,
|
|
"cpu_info": "Intel(R) Xeon(R) Platinum 8480C",
|
|
"gpu_info": "",
|
|
"backends": "CPU",
|
|
"model_filename": "/data/zhoutaichang/.cache/huggingface/hub/models--XHToken--Spark-X2.5-1.7B-GGUF/snapshots/23e1fcac55e7dd71e4c12a23723cc228ba0e5e85/Spark-X2.5-1.7B-Q8_0.gguf",
|
|
"model_type": "spark2_5 1.7B Q8_0",
|
|
"model_size": 1814728704,
|
|
"model_n_params": 1707657216,
|
|
"n_batch": 2048,
|
|
"n_ubatch": 512,
|
|
"n_threads": 8,
|
|
"cpu_mask": "0x0",
|
|
"cpu_strict": false,
|
|
"poll": 50,
|
|
"type_k": "f16",
|
|
"type_v": "f16",
|
|
"n_gpu_layers": -1,
|
|
"n_cpu_moe": 0,
|
|
"split_mode": "layer",
|
|
"main_gpu": 0,
|
|
"no_kv_offload": false,
|
|
"flash_attn": -1,
|
|
"devices": "auto",
|
|
"tensor_split": "0.00",
|
|
"tensor_buft_overrides": "none",
|
|
"load_mode": "auto",
|
|
"lazy_mode": "auto",
|
|
"embeddings": false,
|
|
"no_op_offload": 0,
|
|
"no_host": false,
|
|
"fit_target": 0,
|
|
"fit_min_ctx": 0,
|
|
"n_prompt": 0,
|
|
"n_gen": 128,
|
|
"n_depth": 0,
|
|
"test_time": "2026-09-11T06:29:21Z",
|
|
"avg_ns": 2844703994,
|
|
"stddev_ns": 50284844,
|
|
"avg_ts": 45.007005,
|
|
"stddev_ts": 0.785784,
|
|
"samples_ns": [ 2841360663, 2852415251, 2800656934, 2925026017, 2804061106 ],
|
|
"samples_ts": [ 45.0488, 44.8743, 45.7036, 43.7603, 45.6481 ]
|
|
},
|
|
{
|
|
"build_commit": "e71b80510",
|
|
"build_number": 10849,
|
|
"cpu_info": "Intel(R) Xeon(R) Platinum 8480C",
|
|
"gpu_info": "",
|
|
"backends": "CPU",
|
|
"model_filename": "/data/zhoutaichang/.cache/huggingface/hub/models--XHToken--Spark-X2.5-1.7B-GGUF/snapshots/23e1fcac55e7dd71e4c12a23723cc228ba0e5e85/Spark-X2.5-1.7B-Q4_K_M.gguf",
|
|
"model_type": "spark2_5 1.7B Q4_K - Medium",
|
|
"model_size": 1102073856,
|
|
"model_n_params": 1707657216,
|
|
"n_batch": 2048,
|
|
"n_ubatch": 512,
|
|
"n_threads": 8,
|
|
"cpu_mask": "0x0",
|
|
"cpu_strict": false,
|
|
"poll": 50,
|
|
"type_k": "f16",
|
|
"type_v": "f16",
|
|
"n_gpu_layers": -1,
|
|
"n_cpu_moe": 0,
|
|
"split_mode": "layer",
|
|
"main_gpu": 0,
|
|
"no_kv_offload": false,
|
|
"flash_attn": -1,
|
|
"devices": "auto",
|
|
"tensor_split": "0.00",
|
|
"tensor_buft_overrides": "none",
|
|
"load_mode": "auto",
|
|
"lazy_mode": "auto",
|
|
"embeddings": false,
|
|
"no_op_offload": 0,
|
|
"no_host": false,
|
|
"fit_target": 0,
|
|
"fit_min_ctx": 0,
|
|
"n_prompt": 512,
|
|
"n_gen": 0,
|
|
"n_depth": 0,
|
|
"test_time": "2026-09-11T06:29:36Z",
|
|
"avg_ns": 1179360692,
|
|
"stddev_ns": 9282489,
|
|
"avg_ts": 434.155009,
|
|
"stddev_ts": 3.414034,
|
|
"samples_ns": [ 1190805907, 1173513176, 1168400903, 1186783926, 1177299549 ],
|
|
"samples_ts": [ 429.961, 436.297, 438.206, 431.418, 434.894 ]
|
|
},
|
|
{
|
|
"build_commit": "e71b80510",
|
|
"build_number": 10849,
|
|
"cpu_info": "Intel(R) Xeon(R) Platinum 8480C",
|
|
"gpu_info": "",
|
|
"backends": "CPU",
|
|
"model_filename": "/data/zhoutaichang/.cache/huggingface/hub/models--XHToken--Spark-X2.5-1.7B-GGUF/snapshots/23e1fcac55e7dd71e4c12a23723cc228ba0e5e85/Spark-X2.5-1.7B-Q4_K_M.gguf",
|
|
"model_type": "spark2_5 1.7B Q4_K - Medium",
|
|
"model_size": 1102073856,
|
|
"model_n_params": 1707657216,
|
|
"n_batch": 2048,
|
|
"n_ubatch": 512,
|
|
"n_threads": 8,
|
|
"cpu_mask": "0x0",
|
|
"cpu_strict": false,
|
|
"poll": 50,
|
|
"type_k": "f16",
|
|
"type_v": "f16",
|
|
"n_gpu_layers": -1,
|
|
"n_cpu_moe": 0,
|
|
"split_mode": "layer",
|
|
"main_gpu": 0,
|
|
"no_kv_offload": false,
|
|
"flash_attn": -1,
|
|
"devices": "auto",
|
|
"tensor_split": "0.00",
|
|
"tensor_buft_overrides": "none",
|
|
"load_mode": "auto",
|
|
"lazy_mode": "auto",
|
|
"embeddings": false,
|
|
"no_op_offload": 0,
|
|
"no_host": false,
|
|
"fit_target": 0,
|
|
"fit_min_ctx": 0,
|
|
"n_prompt": 0,
|
|
"n_gen": 128,
|
|
"n_depth": 0,
|
|
"test_time": "2026-09-11T06:29:43Z",
|
|
"avg_ns": 3018952734,
|
|
"stddev_ns": 27599225,
|
|
"avg_ts": 42.401651,
|
|
"stddev_ts": 0.388562,
|
|
"samples_ns": [ 3042267389, 2995063052, 3045385324, 2984815648, 3027232258 ],
|
|
"samples_ts": [ 42.0739, 42.737, 42.0308, 42.8837, 42.2828 ]
|
|
}
|
|
]
|