Skip to page content
SAVRN
Search Plan a project

Dataset

vllm-inference-benchmarks

by ScaleDown scaledown/vllm-inference-benchmarks

Rows—
Configurations—
Size3.3 MB
License—
AccessPublicly accessible
Monthly Downloads—

Dataset Card

The publisher has not written a card for this dataset.

Details

Repository
scaledown/vllm-inference-benchmarks
Publisher
ScaleDown
Task category
Not stated by the source
Tags
Not stated by the source
Size category
Not stated by the source
Languages
Not stated by the source
Revision
24fcd7470c12f2e39d97709ebf4f5a4ab607e26a
Last updated
2026-09-27

Files

102 files, 3.3 MB in total.

Data88 files · 275.2 KB
Other13 files · 3.0 MB
Repository1 file · 2.5 KB
Every file
FileTypeSizeSHA-256
_hf_upload_test.csvData58 B—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs32_batched12288_conc16_run1.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs32_batched12288_conc16_run2.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs32_batched12288_conc24_run1.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs32_batched12288_conc24_run2.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs32_batched12288_conc32_run1.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs32_batched12288_conc32_run2.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs32_batched12288_conc8_run1.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs32_batched12288_conc8_run2.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs32_batched12288_conc8_warmup.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs64_batched24576_conc16_run1.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs64_batched24576_conc16_run2.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs64_batched24576_conc24_run1.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs64_batched24576_conc24_run2.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs64_batched24576_conc32_run1.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs64_batched24576_conc32_run2.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs64_batched24576_conc48_run1.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs64_batched24576_conc48_run2.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs64_batched24576_conc64_run1.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs64_batched24576_conc64_run2.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs64_batched24576_conc8_run1.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs64_batched24576_conc8_run2.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/seqs64_batched24576_conc8_warmup.jsonData1.6 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs32_batched12288_conc16_run1.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs32_batched12288_conc16_run2.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs32_batched12288_conc24_run1.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs32_batched12288_conc24_run2.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs32_batched12288_conc32_run1.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs32_batched12288_conc32_run2.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs32_batched12288_conc8_run1.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs32_batched12288_conc8_run2.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs32_batched12288_conc8_warmup.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs64_batched16384_conc16_run1.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs64_batched16384_conc16_run2.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs64_batched16384_conc24_run1.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs64_batched16384_conc24_run2.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs64_batched16384_conc32_run1.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs64_batched16384_conc32_run2.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs64_batched16384_conc48_run1.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs64_batched16384_conc48_run2.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs64_batched16384_conc64_run1.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs64_batched16384_conc64_run2.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs64_batched16384_conc8_run1.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs64_batched16384_conc8_run2.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/seqs64_batched16384_conc8_warmup.jsonData2.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs32_batched16384_conc16_run1.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs32_batched16384_conc16_run2.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs32_batched16384_conc24_run1.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs32_batched16384_conc24_run2.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs32_batched16384_conc32_run1.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs32_batched16384_conc32_run2.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs32_batched16384_conc8_run1.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs32_batched16384_conc8_run2.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs32_batched16384_conc8_warmup.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs64_batched32768_conc16_run1.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs64_batched32768_conc16_run2.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs64_batched32768_conc24_run1.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs64_batched32768_conc24_run2.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs64_batched32768_conc32_run1.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs64_batched32768_conc32_run2.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs64_batched32768_conc48_run1.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs64_batched32768_conc48_run2.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs64_batched32768_conc64_run1.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs64_batched32768_conc64_run2.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs64_batched32768_conc8_run1.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs64_batched32768_conc8_run2.jsonData1.9 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/seqs64_batched32768_conc8_warmup.jsonData1.9 KB—
logs/smoke/qwen3.6-27b-fp8__base/result_run1.jsonData1.6 KB—
logs/smoke/qwen3.6-27b-fp8__base/result_run2.jsonData1.6 KB—
logs/smoke/qwen3.6-27b-fp8__base/result_warmup.jsonData1.6 KB—
logs/smoke/qwen3.6-27b-fp8__dflash/result_run1.jsonData2.0 KB—
logs/smoke/qwen3.6-27b-fp8__dflash/result_run2.jsonData2.1 KB—
logs/smoke/qwen3.6-27b-fp8__dflash/result_warmup.jsonData1.9 KB—
logs/smoke/qwen3.6-27b-fp8__mtp/result_run1.jsonData1.8 KB—
logs/smoke/qwen3.6-27b-fp8__mtp/result_run2.jsonData1.8 KB—
logs/smoke/qwen3.6-27b-fp8__mtp/result_warmup.jsonData1.8 KB—
logs/smoke/qwen3.6-27b__base/result_run1.jsonData1.6 KB—
logs/smoke/qwen3.6-27b__base/result_run2.jsonData1.6 KB—
logs/smoke/qwen3.6-27b__base/result_warmup.jsonData1.5 KB—
logs/smoke/qwen3.6-27b__dflash/result_run1.jsonData2.0 KB—
logs/smoke/qwen3.6-27b__dflash/result_run2.jsonData2.0 KB—
logs/smoke/qwen3.6-27b__dflash/result_warmup.jsonData1.9 KB—
logs/smoke/qwen3.6-27b__mtp/result_run1.jsonData1.8 KB—
logs/smoke/qwen3.6-27b__mtp/result_run2.jsonData1.8 KB—
logs/smoke/qwen3.6-27b__mtp/result_warmup.jsonData1.8 KB—
orchestrate_results.csvData85.9 KB—
orchestrate_results.pre_20260926_213555.csvData3.0 KB—
orchestrate_state.jsonData29.2 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/server_seqs32_batched12288.logOther279.5 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__base/server_seqs64_batched24576.logOther611.8 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/server_seqs32_batched12288.logOther298.4 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__dflash/server_seqs64_batched16384.logOther638.7 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/server_seqs32_batched16384.logOther291.4 KB—
logs/phase2/qwen3.6-35b-a3b-fp8__mtp/server_seqs64_batched32768.logOther630.0 KB—
logs/smoke/qwen3.6-27b-fp8__base/server_smoke.logOther42.7 KB—
logs/smoke/qwen3.6-27b-fp8__dflash/server_smoke.logOther44.2 KB—
logs/smoke/qwen3.6-27b-fp8__mtp/server_smoke.logOther42.8 KB—
logs/smoke/qwen3.6-27b__base/server_smoke.logOther34.4 KB—
logs/smoke/qwen3.6-27b__dflash/server_smoke.logOther40.6 KB—
logs/smoke/qwen3.6-27b__mtp/server_smoke.logOther38.9 KB—
orchestrate_progress.logOther32.1 KB—
.gitattributesRepository2.5 KB—

License and Download

License
Not stated by the source
Access
No access gate
Download from ScaleDown

Released by ScaleDown through its official repository on Hugging Face.