anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
Files
67eb7fdb485a1aaf3207b895cc3cc0c99030a975
vllm-omni/probe/issue-2/evidence/rtx3090/runs-summary.json
T
admin 67eb7fdb48
Build Wheel / build (3.11) (pull_request) Failing after 33s
Details
Build Wheel / build (3.12) (pull_request) Failing after 40s
Details
pre-commit / pre-commit (pull_request) Failing after 41s
Details
probe: Qwen-Image conditioning-KV spill probe on RTX 3090 / RTX 5080 (issue 2) 
Evidence-only change: probe kit (serve wrapper, API client, PSNR
comparator, offline fp8_v driver), per-host run summaries, and the
findings report. No code changes to the stack.

Verdicts: not-built on both cards. On the 3090 the served reference
ceiling is two condition images with the conditioning cache on
(2.2x the Diffusers nocache baseline, pair PSNR mean 27.57 dB);
four references OOM on the resident BF16 working set, not the KV
(~0.3 GiB/reference, per-request). On the 5080 the server cannot
initialize under any flag: init_parameters materializes the
unquantized skeleton on-device before quantization/offload engage.
Also documents that the recipe's deploy-YAML extras route for
prefix_kv_cache_dtype does not reach the served transformer on
8484d85d (offline Omni engine kwarg does).
2026-10-08 00:58:29 -04:00

647 lines
23 KiB
JSON
Raw Blame History

{
"runs": {
"cpuoff": {
"flags": "--enable-cpu-offload",
"vram_peak_mib": 24015,
"functional.json": [
{
"fixture_id": "edit-expression-ysolde",
"seed": 2301,
"n_references": 1,
"steps": 20,
"true_cfg_scale": 1.0,
"size": "864x1152",
"wall_s": 34.16,
"http": 200,
"bytes": 3983827,
"sha256": "3c4eb2ef129dbf8afe518b32069cdd9db7811cdedf3ac09557398de193bff972",
"usage": null,
"metrics": {
"stage_metrics": {
"0": {
"stage_id": 0,
"final_output_type": "image",
"finish_reason": null,
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_gen_time_ms": 34077.84652709961,
"postprocess_time_ms": 0.0,
"audio_frames": 0,
"audio_sample_rate": 0,
"audio_duration_s": 0.0,
"image_pixels": 995328,
"denoise_step_latency_ms": 1703.8923263549805,
"output_unit_type": "image",
"output_unit_count": 1,
"serving_time_to_first_output_ms": 34078.10688018799,
"image_time_to_first_output_ms": 34077.83102989197,
"time_per_output_unit_ms": 0.0,
"inter_output_latency_ms": 0.0,
"inter_output_latencies_ms": [],
"vllm_ttft_ms": 0.0,
"vllm_tpot_ms": 0.0,
"vllm_itl_ms": 0.0,
"vllm_itls_ms": [],
"stage_name": "diffusion"
}
},
"stage_id": 0,
"final_output_type": "image",
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_durations": {
"queue_wait_ms": 0.23758299903420266,
"stage_0_gen_ms": 34077.84652709961
},
"peak_memory_mb": 23444.0
}
},
{
"fixture_id": "edit-compose-pair",
"seed": 2301,
"n_references": 2,
"steps": 20,
"true_cfg_scale": 1.0,
"size": "1248x832",
"wall_s": 36.68,
"http": 200,
"bytes": 4155590,
"sha256": "45fac0b8683cac36d4741f71bd1233b66b41b41b2e322c5a870fb6bc303b2ec4",
"usage": null,
"metrics": {
"stage_metrics": {
"0": {
"stage_id": 0,
"final_output_type": "image",
"finish_reason": null,
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_gen_time_ms": 36615.47255516052,
"postprocess_time_ms": 0.0,
"audio_frames": 0,
"audio_sample_rate": 0,
"audio_duration_s": 0.0,
"image_pixels": 1038336,
"denoise_step_latency_ms": 1830.7736277580261,
"output_unit_type": "image",
"output_unit_count": 1,
"serving_time_to_first_output_ms": 36615.6051158905,
"image_time_to_first_output_ms": 36615.44394493103,
"time_per_output_unit_ms": 0.0,
"inter_output_latency_ms": 0.0,
"inter_output_latencies_ms": [],
"vllm_ttft_ms": 0.0,
"vllm_tpot_ms": 0.0,
"vllm_itl_ms": 0.0,
"vllm_itls_ms": [],
"stage_name": "diffusion"
}
},
"stage_id": 0,
"final_output_type": "image",
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_durations": {
"queue_wait_ms": 0.12273299944354221,
"stage_0_gen_ms": 36615.47255516052
},
"peak_memory_mb": 23638.0
}
},
{
"fixture_id": "edit-compose-four",
"seed": 2301,
"n_references": 4,
"steps": 20,
"true_cfg_scale": 1.0,
"size": "1344x768",
"wall_s": 12.24,
"http": 500,
"error": "{\"error\":{\"message\":\"Image edit failed: CUDA out of memory. Tried to allocate 490.00 MiB. GPU 0 has a total capacity of 23.61 GiB of which 306.38 MiB is free. Including non-PyTorch memory, this process has 23.18 GiB memory in use. Of the allocated memory 21.02 GiB is allocated by PyTorch, and 1.84 GiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://docs.pytorch.org<path>#optimizing-memory-usage-with-pytorch-cuda-alloc-conf)\",\"type\":\"Internal Server Error\",\"param\":null,\"code\":500}}"
}
]
},
"cpuoff-expandable": {
"flags": "--enable-cpu-offload",
"vram_peak_mib": 24095,
"functional.json": [
{
"fixture_id": "edit-expression-ysolde",
"seed": 2301,
"n_references": 1,
"steps": 20,
"true_cfg_scale": 1.0,
"size": "864x1152",
"wall_s": 33.84,
"http": 200,
"bytes": 3983827,
"sha256": "3c4eb2ef129dbf8afe518b32069cdd9db7811cdedf3ac09557398de193bff972",
"usage": null,
"metrics": {
"stage_metrics": {
"0": {
"stage_id": 0,
"final_output_type": "image",
"finish_reason": null,
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_gen_time_ms": 33751.58882141113,
"postprocess_time_ms": 0.0,
"audio_frames": 0,
"audio_sample_rate": 0,
"audio_duration_s": 0.0,
"image_pixels": 995328,
"denoise_step_latency_ms": 1687.5794410705566,
"output_unit_type": "image",
"output_unit_count": 1,
"serving_time_to_first_output_ms": 33751.80244445801,
"image_time_to_first_output_ms": 33751.57427787781,
"time_per_output_unit_ms": 0.0,
"inter_output_latency_ms": 0.0,
"inter_output_latencies_ms": [],
"vllm_ttft_ms": 0.0,
"vllm_tpot_ms": 0.0,
"vllm_itl_ms": 0.0,
"vllm_itls_ms": [],
"stage_name": "diffusion"
}
},
"stage_id": 0,
"final_output_type": "image",
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_durations": {
"queue_wait_ms": 0.19045899898628704,
"stage_0_gen_ms": 33751.58882141113
},
"peak_memory_mb": 21458.0
}
},
{
"fixture_id": "edit-compose-pair",
"seed": 2301,
"n_references": 2,
"steps": 20,
"true_cfg_scale": 1.0,
"size": "1248x832",
"wall_s": 36.68,
"http": 200,
"bytes": 4155590,
"sha256": "45fac0b8683cac36d4741f71bd1233b66b41b41b2e322c5a870fb6bc303b2ec4",
"usage": null,
"metrics": {
"stage_metrics": {
"0": {
"stage_id": 0,
"final_output_type": "image",
"finish_reason": null,
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_gen_time_ms": 36616.71161651611,
"postprocess_time_ms": 0.0,
"audio_frames": 0,
"audio_sample_rate": 0,
"audio_duration_s": 0.0,
"image_pixels": 1038336,
"denoise_step_latency_ms": 1830.8355808258057,
"output_unit_type": "image",
"output_unit_count": 1,
"serving_time_to_first_output_ms": 36616.929054260254,
"image_time_to_first_output_ms": 36616.68133735657,
"time_per_output_unit_ms": 0.0,
"inter_output_latency_ms": 0.0,
"inter_output_latencies_ms": [],
"vllm_ttft_ms": 0.0,
"vllm_tpot_ms": 0.0,
"vllm_itl_ms": 0.0,
"vllm_itls_ms": [],
"stage_name": "diffusion"
}
},
"stage_id": 0,
"final_output_type": "image",
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_durations": {
"queue_wait_ms": 0.1754260010784492,
"stage_0_gen_ms": 36616.71161651611
},
"peak_memory_mb": 21896.0
}
},
{
"fixture_id": "edit-compose-four",
"seed": 2301,
"n_references": 4,
"steps": 20,
"true_cfg_scale": 1.0,
"size": "1344x768",
"wall_s": 13.39,
"http": 500,
"error": "{\"error\":{\"message\":\"Image edit failed: CUDA out of memory. Tried to allocate 490.00 MiB. GPU 0 has a total capacity of 23.61 GiB of which 382.38 MiB is free. Including non-PyTorch memory, this process has 23.11 GiB memory in use. Of the allocated memory 22.29 GiB is allocated by PyTorch, and 505.35 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://docs.pytorch.org<path>#optimizing-memory-usage-with-pytorch-cuda-alloc-conf)\",\"type\":\"Internal Server Error\",\"param\":null,\"code\":500}}"
}
],
"measured-edit-compose-pair.json": [
{
"fixture_id": "edit-compose-pair",
"seed": 2301,
"n_references": 2,
"steps": 20,
"true_cfg_scale": 1.0,
"size": "1248x832",
"wall_s": 36.61,
"http": 200,
"bytes": 4155590,
"sha256": "45fac0b8683cac36d4741f71bd1233b66b41b41b2e322c5a870fb6bc303b2ec4",
"usage": null,
"metrics": {
"stage_metrics": {
"0": {
"stage_id": 0,
"final_output_type": "image",
"finish_reason": null,
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_gen_time_ms": 36539.32213783264,
"postprocess_time_ms": 0.0,
"audio_frames": 0,
"audio_sample_rate": 0,
"audio_duration_s": 0.0,
"image_pixels": 1038336,
"denoise_step_latency_ms": 1826.966106891632,
"output_unit_type": "image",
"output_unit_count": 1,
"serving_time_to_first_output_ms": 36539.42966461182,
"image_time_to_first_output_ms": 36539.30997848511,
"time_per_output_unit_ms": 0.0,
"inter_output_latency_ms": 0.0,
"inter_output_latencies_ms": [],
"vllm_ttft_ms": 0.0,
"vllm_tpot_ms": 0.0,
"vllm_itl_ms": 0.0,
"vllm_itls_ms": [],
"stage_name": "diffusion"
}
},
"stage_id": 0,
"final_output_type": "image",
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_durations": {
"queue_wait_ms": 0.09375800073030405,
"stage_0_gen_ms": 36539.32213783264
},
"peak_memory_mb": 23332.0
}
},
{
"fixture_id": "edit-compose-pair",
"seed": 2302,
"n_references": 2,
"steps": 20,
"true_cfg_scale": 1.0,
"size": "1248x832",
"wall_s": 36.71,
"http": 200,
"bytes": 4155590,
"sha256": "e45a25c5b45ac7b1818843d2f589d164f3f780432472a692defc7569b5c28419",
"usage": null,
"metrics": {
"stage_metrics": {
"0": {
"stage_id": 0,
"final_output_type": "image",
"finish_reason": null,
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_gen_time_ms": 36643.63503456116,
"postprocess_time_ms": 0.0,
"audio_frames": 0,
"audio_sample_rate": 0,
"audio_duration_s": 0.0,
"image_pixels": 1038336,
"denoise_step_latency_ms": 1832.1817517280579,
"output_unit_type": "image",
"output_unit_count": 1,
"serving_time_to_first_output_ms": 36643.73755455017,
"image_time_to_first_output_ms": 36643.60785484314,
"time_per_output_unit_ms": 0.0,
"inter_output_latency_ms": 0.0,
"inter_output_latencies_ms": [],
"vllm_ttft_ms": 0.0,
"vllm_tpot_ms": 0.0,
"vllm_itl_ms": 0.0,
"vllm_itls_ms": [],
"stage_name": "diffusion"
}
},
"stage_id": 0,
"final_output_type": "image",
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_durations": {
"queue_wait_ms": 0.10074199963128194,
"stage_0_gen_ms": 36643.63503456116
},
"peak_memory_mb": 21976.0
}
},
{
"fixture_id": "edit-compose-pair",
"seed": 2303,
"n_references": 2,
"steps": 20,
"true_cfg_scale": 1.0,
"size": "1248x832",
"wall_s": 36.84,
"http": 200,
"bytes": 4155590,
"sha256": "7cf52663ff4691833241766a7c7aa45b373ff54044599887f8bab0e2519c7846",
"usage": null,
"metrics": {
"stage_metrics": {
"0": {
"stage_id": 0,
"final_output_type": "image",
"finish_reason": null,
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_gen_time_ms": 36772.2589969635,
"postprocess_time_ms": 0.0,
"audio_frames": 0,
"audio_sample_rate": 0,
"audio_duration_s": 0.0,
"image_pixels": 1038336,
"denoise_step_latency_ms": 1838.612949848175,
"output_unit_type": "image",
"output_unit_count": 1,
"serving_time_to_first_output_ms": 36771.2607383728,
"image_time_to_first_output_ms": 36771.116733551025,
"time_per_output_unit_ms": 0.0,
"inter_output_latency_ms": 0.0,
"inter_output_latencies_ms": [],
"vllm_ttft_ms": 0.0,
"vllm_tpot_ms": 0.0,
"vllm_itl_ms": 0.0,
"vllm_itls_ms": [],
"stage_name": "diffusion"
}
},
"stage_id": 0,
"final_output_type": "image",
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_durations": {
"queue_wait_ms": 0.11694399836414959,
"stage_0_gen_ms": 36772.2589969635
},
"peak_memory_mb": 21996.0
}
},
{
"fixture_id": "edit-compose-pair",
"seed": 2304,
"n_references": 2,
"steps": 20,
"true_cfg_scale": 1.0,
"size": "1248x832",
"wall_s": 36.93,
"http": 200,
"bytes": 4155590,
"sha256": "54ab259e4669e0b24f900956c37d031d8462501b5e37246b9ce7d2a8d1c8f3fe",
"usage": null,
"metrics": {
"stage_metrics": {
"0": {
"stage_id": 0,
"final_output_type": "image",
"finish_reason": null,
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_gen_time_ms": 36872.36309051514,
"postprocess_time_ms": 0.0,
"audio_frames": 0,
"audio_sample_rate": 0,
"audio_duration_s": 0.0,
"image_pixels": 1038336,
"denoise_step_latency_ms": 1843.6181545257568,
"output_unit_type": "image",
"output_unit_count": 1,
"serving_time_to_first_output_ms": 36871.95873260498,
"image_time_to_first_output_ms": 36871.82974815369,
"time_per_output_unit_ms": 0.0,
"inter_output_latency_ms": 0.0,
"inter_output_latencies_ms": [],
"vllm_ttft_ms": 0.0,
"vllm_tpot_ms": 0.0,
"vllm_itl_ms": 0.0,
"vllm_itls_ms": [],
"stage_name": "diffusion"
}
},
"stage_id": 0,
"final_output_type": "image",
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_durations": {
"queue_wait_ms": 0.10266400022374,
"stage_0_gen_ms": 36872.36309051514
},
"peak_memory_mb": 21996.0
}
}
]
},
"cpuoff-fp8v": {
"flags": "--enable-cpu-offload --deploy-config /home/anodyine/Projects/vllm-omni-val/issue2/deploy-fp8v.yaml",
"vram_peak_mib": 24015,
"functional.json": [
{
"fixture_id": "edit-expression-ysolde",
"seed": 2301,
"n_references": 1,
"steps": 20,
"true_cfg_scale": 1.0,
"size": "864x1152",
"wall_s": 34.32,
"http": 200,
"bytes": 3983827,
"sha256": "3c4eb2ef129dbf8afe518b32069cdd9db7811cdedf3ac09557398de193bff972",
"usage": null,
"metrics": {
"stage_metrics": {
"0": {
"stage_id": 0,
"final_output_type": "image",
"finish_reason": null,
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_gen_time_ms": 34243.89171600342,
"postprocess_time_ms": 0.0,
"audio_frames": 0,
"audio_sample_rate": 0,
"audio_duration_s": 0.0,
"image_pixels": 995328,
"denoise_step_latency_ms": 1712.194585800171,
"output_unit_type": "image",
"output_unit_count": 1,
"serving_time_to_first_output_ms": 34244.08268928528,
"image_time_to_first_output_ms": 34243.87454986572,
"time_per_output_unit_ms": 0.0,
"inter_output_latency_ms": 0.0,
"inter_output_latencies_ms": [],
"vllm_ttft_ms": 0.0,
"vllm_tpot_ms": 0.0,
"vllm_itl_ms": 0.0,
"vllm_itls_ms": [],
"stage_name": "diffusion"
}
},
"stage_id": 0,
"final_output_type": "image",
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_durations": {
"queue_wait_ms": 0.16898400099307764,
"stage_0_gen_ms": 34243.89171600342
},
"peak_memory_mb": 23444.0
}
},
{
"fixture_id": "edit-compose-pair",
"seed": 2301,
"n_references": 2,
"steps": 20,
"true_cfg_scale": 1.0,
"size": "1248x832",
"wall_s": 36.78,
"http": 200,
"bytes": 4155590,
"sha256": "45fac0b8683cac36d4741f71bd1233b66b41b41b2e322c5a870fb6bc303b2ec4",
"usage": null,
"metrics": {
"stage_metrics": {
"0": {
"stage_id": 0,
"final_output_type": "image",
"finish_reason": null,
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_gen_time_ms": 36713.937759399414,
"postprocess_time_ms": 0.0,
"audio_frames": 0,
"audio_sample_rate": 0,
"audio_duration_s": 0.0,
"image_pixels": 1038336,
"denoise_step_latency_ms": 1835.6968879699707,
"output_unit_type": "image",
"output_unit_count": 1,
"serving_time_to_first_output_ms": 36714.062213897705,
"image_time_to_first_output_ms": 36713.90199661255,
"time_per_output_unit_ms": 0.0,
"inter_output_latency_ms": 0.0,
"inter_output_latencies_ms": [],
"vllm_ttft_ms": 0.0,
"vllm_tpot_ms": 0.0,
"vllm_itl_ms": 0.0,
"vllm_itls_ms": [],
"stage_name": "diffusion"
}
},
"stage_id": 0,
"final_output_type": "image",
"num_tokens_in": 0,
"num_tokens_out": 0,
"stage_durations": {
"queue_wait_ms": 0.12299100126256235,
"stage_0_gen_ms": 36713.937759399414
},
"peak_memory_mb": 23638.0
}
},
{
"fixture_id": "edit-compose-four",
"seed": 2301,
"n_references": 4,
"steps": 20,
"true_cfg_scale": 1.0,
"size": "1344x768",
"wall_s": 12.25,
"http": 500,
"error": "{\"error\":{\"message\":\"Image edit failed: CUDA out of memory. Tried to allocate 490.00 MiB. GPU 0 has a total capacity of 23.61 GiB of which 306.38 MiB is free. Including non-PyTorch memory, this process has 23.18 GiB memory in use. Of the allocated memory 21.02 GiB is allocated by PyTorch, and 1.84 GiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://docs.pytorch.org<path>#optimizing-memory-usage-with-pytorch-cuda-alloc-conf)\",\"type\":\"Internal Server Error\",\"param\":null,\"code\":500}}"
}
]
},
"cpuoff-layerwise": {
"flags": "--enable-cpu-offload --enable-layerwise-offload",
"vram_peak_mib": 24137,
"functional.json": [
{
"fixture_id": "edit-expression-ysolde",
"seed": 2301,
"n_references": 1,
"steps": 20,
"true_cfg_scale": 1.0,
"size": "864x1152",
"wall_s": 26.18,
"http": 500,
"error": "{\"error\":{\"message\":\"Image edit failed: CUDA out of memory. Tried to allocate 1.07 GiB. GPU 0 has a total capacity of 23.61 GiB of which 602.38 MiB is free. Including non-PyTorch memory, this process has 22.94 GiB memory in use. Of the allocated memory 21.76 GiB is allocated by PyTorch, and 852.17 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://docs.pytorch.org<path>#optimizing-memory-usage-with-pytorch-cuda-alloc-conf)\",\"type\":\"Internal Server Error\",\"param\":null,\"code\":500}}"
},
{
"fixture_id": "edit-compose-pair",
"seed": 2301,
"n_references": 2,
"steps": 20,
"true_cfg_scale": 1.0,
"size": "1248x832",
"wall_s": 3.32,
"http": 500,
"error": "{\"error\":{\"message\":\"Image edit failed: CUDA out of memory. Tried to allocate 296.00 MiB. GPU 0 has a total capacity of 23.61 GiB of which 40.38 MiB is free. Including non-PyTorch memory, this process has 23.49 GiB memory in use. Of the allocated memory 21.88 GiB is allocated by PyTorch, and 1.26 GiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://docs.pytorch.org<path>#optimizing-memory-usage-with-pytorch-cuda-alloc-conf)\",\"type\":\"Internal Server Error\",\"param\":null,\"code\":500}}"
},
{
"fixture_id": "edit-compose-four",
"seed": 2301,
"n_references": 4,
"steps": 20,
"true_cfg_scale": 1.0,
"size": "1344x768",
"wall_s": 3.1,
"http": 500,
"error": "{\"error\":{\"message\":\"Image edit failed: CUDA out of memory. Tried to allocate 490.00 MiB. GPU 0 has a total capacity of 23.61 GiB of which 290.38 MiB is free. Including non-PyTorch memory, this process has 23.24 GiB memory in use. Of the allocated memory 21.87 GiB is allocated by PyTorch, and 1.03 GiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://docs.pytorch.org<path>#optimizing-memory-usage-with-pytorch-cuda-alloc-conf)\",\"type\":\"Internal Server Error\",\"param\":null,\"code\":500}}"
}
]
},
"default": {
"flags": "flags:",
"serve_rc": 1,
"serve_wall_s": 14,
"vram_peak_mib": 23939
},
"offline-fp8v": {
"offline-edit-compose-four.json": [
{
"fixture_id": "edit-compose-four",
"seed": 2301,
"n_references": 4,
"kv_dtype": "fp8_v",
"wall_s": 15.91,
"error": "RuntimeError: CUDA out of memory. Tried to allocate 490.00 MiB. GPU 0 has a total capacity of 23.61 GiB of which 162.38 MiB is free. Including non-PyTorch memory, this process has 23.32 GiB memory in use. Of the allocated memory 20.86 GiB is allocated by PyTorch, and 2.14 GiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://docs.pytorch.org/docs/stable/notes/cuda.html#optimizing-memory-usage-with-pytorch-cuda-alloc-conf)"
}
]
},
"offline-fp8v-expandable": {
"offline-edit-compose-four.json": [
{
"fixture_id": "edit-compose-four",
"seed": 2301,
"n_references": 4,
"kv_dtype": "fp8_v",
"wall_s": 17.83,
"error": "RuntimeError: CUDA out of memory. Tried to allocate 490.00 MiB. GPU 0 has a total capacity of 23.61 GiB of which 482.38 MiB is free. Including non-PyTorch memory, this process has 23.01 GiB memory in use. Of the allocated memory 22.22 GiB is allocated by PyTorch, and 483.06 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://docs.pytorch.org/docs/stable/notes/cuda.html#optimizing-memory-usage-with-pytorch-cuda-alloc-conf)"
}
]
}
}
}
Reference in new issue View Git Blame Copy Permalink