Inference Optimization

community

AI & ML interests

None defined yet.

Recent Activity

kylesayrs updated a model 3 days ago

inference-optimization/Kimi-K3-0.40B-MXFP4

nm-research updated a model 4 days ago

inference-optimization/qwe3-8B-selfdistill-v3-fresh3ep_ckpt2

nm-research published a model 4 days ago

inference-optimization/qwe3-8B-selfdistill-v3-fresh3ep_ckpt2

View all activity

inference-optimization 's models 446

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw.2048anc-qwen235b-instr-bs16-v3-10ep-ckpt6

2B • Updated Jul 27 • 5

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw.2048anc-qwen235b-instr-bs16-v3-10ep-ckpt5

2B • Updated Jul 27 • 6

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw.2048anc-qwen235b-instr-bs16-v3-10ep-ckpt4

2B • Updated Jul 27 • 6

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw.2048anc-qwen235b-instr-bs16-v3-10ep-ckpt3

2B • Updated Jul 27 • 7

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw.2048anc-qwen235b-instr-bs16-v3-10ep-ckpt2

2B • Updated Jul 27 • 7

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw.2048anc-qwen235b-instr-bs16-v3-10ep-ckpt1

2B • Updated Jul 27 • 12

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw.2048anc-qwen235b-instr-bs16-v3-10ep-ckpt0

2B • Updated Jul 27 • 9

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw.2048anchors-qwen235b-instruct-bs16-v3-ckpt6

2B • Updated Jul 27 • 6

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw.2048anchors-qwen235b-instruct-bs16-v3-ckpt5

2B • Updated Jul 26 • 6

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw.2048anchors-qwen235b-instruct-bs16-v3-ckpt4

2B • Updated Jul 26 • 7

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw.2048anchors-qwen235b-instruct-bs16-v3-ckpt3

2B • Updated Jul 26 • 5

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw.2048anchors-qwen235b-instruct-bs16-v3-ckpt2

2B • Updated Jul 26 • 6

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw.2048anchors-qwen235b-instruct-bs16-v3-ckpt1

2B • Updated Jul 25 • 6

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw.2048anchors-qwen235b-instruct-bs16-v3-ckpt0

2B • Updated Jul 25 • 6

inference-optimization/tmp-max-anchors-ablation-2048

2B • Updated Jul 24 • 4

inference-optimization/tmp-max-anchors-ablation-1536

2B • Updated Jul 24 • 5

inference-optimization/tmp-max-anchors-ablation-1024

2B • Updated Jul 24 • 3

inference-optimization/tmp-max-anchors-ablation-512

2B • Updated Jul 24 • 3

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw-qwen235b-instruct-bs16-v2-ckpt9

2B • Updated Jul 23 • 7

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw-qwen235b-instruct-bs16-v2-ckpt8

2B • Updated Jul 23 • 7

inference-optimization/tmp-qwen-mod

Updated Jul 23 • 7

inference-optimization/Qwen3.5-397B-A17B-FP8-dynamic-mtp-head

Image-Text-to-Text • 404B • Updated Jul 23 • 9

inference-optimization/DeepSeek-V4-Pro-0.5B-A0.37B-NVFP4-FP8

0.4B • Updated Jul 22 • 11

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw-qwen235b-instruct-bs16-v2-ckpt7

2B • Updated Jul 22 • 7

inference-optimization/DeepSeek-V4-Pro-0.5B-A0.37B

Text Generation • 0.5B • Updated Jul 22 • 370

inference-optimization/temporary-3-layer-Qwen3-VL-1.0B-A0.4B-Instruct

Image-Text-to-Text • 1B • Updated Jul 22 • 7

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw-qwen235b-instruct-bs16-v2-ckpt6

2B • Updated Jul 22 • 9

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.muon-qwen235b-instruct-bs16-v2-ckpt0

2B • Updated Jul 22 • 7

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.muon-qwen235b-instruct-bs16-v2-ckpt8

2B • Updated Jul 22 • 8

inference-optimization/Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.adamw-qwen235b-instruct-bs16-v2-ckpt5

2B • Updated Jul 22 • 7