156 GB

Ctrl+K

1 contributor

History: 104 commits

9bow

Add qwen35-08b-fp32-int8-attn-int4-mlp-gptq-home-token-major-v2-v6 (column-per-lane gated delta rule) (part 3)

d907369 verified 2 days ago

exaone-deep-fp32-8k-state-alias-token-major-v2-v3
Add exaone-deep-fp32-8k-state-alias-token-major-v2-v3 (fused attention, view elision, packed GEMV) 3 days ago
exaone-deep-fp32-8k-state-alias-token-major-v2-v4
Add exaone-deep-fp32-8k-state-alias-token-major-v2-v4 (tiled prefill GEMM over the v3 bundle) 2 days ago
exaone-deep-fp32-8k-state-alias-token-major-v2-v5
Add exaone-deep-fp32-8k-state-alias-token-major-v2-v5 (attention bounded by the used context) 2 days ago
exaone-deep-fp32-8k-state-alias-token-major-v2
Publish WebTorch model catalog bundles (part 2) 28 days ago
exaone-deep-fp32-int8-g32-candidate-token-major-v2-v3
Add exaone-deep-fp32-int8-g32-candidate-token-major-v2-v3 (fused attention, view elision, packed GEMV, INT8 vocabulary) 3 days ago
exaone-deep-fp32-int8-g32-candidate-token-major-v2-v4
Add exaone-deep-fp32-int8-g32-candidate-token-major-v2-v4 (tiled prefill GEMM over the v3 bundle) 2 days ago
exaone-deep-fp32-int8-g32-candidate-token-major-v2-v5
Add exaone-deep-fp32-int8-g32-candidate-token-major-v2-v5 (attention bounded by the used context) 2 days ago
exaone-deep-fp32-int8-g32-candidate-token-major-v2
Publish WebTorch model catalog bundles (part 2) 28 days ago
exaone4-fp16-int4-g32-home-token-major-v2
Add exaone4-fp16-int4-g32-home-token-major-v2 WebTorch bundle 17 days ago
exaone4-fp32-8k-state-alias-token-major-v2-v3
Add exaone4-fp32-8k-state-alias-token-major-v2-v3 (fused attention, view elision, packed GEMV) 3 days ago
exaone4-fp32-8k-state-alias-token-major-v2-v4
Add exaone4-fp32-8k-state-alias-token-major-v2-v4 (tiled prefill GEMM over the v3 bundle) 2 days ago
exaone4-fp32-8k-state-alias-token-major-v2-v5
Add exaone4-fp32-8k-state-alias-token-major-v2-v5 (attention bounded by the used context) 2 days ago
exaone4-fp32-8k-state-alias-token-major-v2
Publish WebTorch model catalog bundles (part 3) 28 days ago
exaone4-fp32-int4-g32-gptq-home-token-major-v2-v3
Add exaone4-fp32-int4-g32-gptq-home-token-major-v2-v3 (fused attention, view elision, packed GEMV, INT8 vocabulary) 3 days ago
exaone4-fp32-int8-g32-release-token-major-v2-v3
Add exaone4-fp32-int8-g32-release-token-major-v2-v3 (fused attention, view elision, packed GEMV, INT8 vocabulary) 3 days ago
exaone4-fp32-int8-g32-release-token-major-v2-v4
Add exaone4-fp32-int8-g32-release-token-major-v2-v4 (tiled prefill GEMM over the v3 bundle) 2 days ago
exaone4-fp32-int8-g32-release-token-major-v2-v5
Fix exaone4-fp32-int8-g32-release-token-major-v2-v5: drop the stale shader-f16 requirement 2 days ago
exaone4-fp32-int8-g32-release-token-major-v2
Publish WebTorch model catalog bundles (part 4) 28 days ago
qwen35-08b-fp16-int4-g32-gptq-home
Add Qwen3.5-0.8B FP16 INT4 GPTQ experiment 27 days ago
qwen35-08b-fp16-int4-g8-gptq-up-proj-exclude-l15-candidate
Add Qwen3.5-0.8B mixed FP16 INT4 candidate (part 2) 27 days ago
qwen35-08b-fp32-8k-token-major-home-v3
Add qwen35-08b-fp32-8k-token-major-home-v3 (fused attention, view elision, packed GEMV) (part 2) 3 days ago
qwen35-08b-fp32-8k-token-major-home-v4
Add qwen35-08b-fp32-8k-token-major-home-v4 (tiled prefill GEMM over the v3 bundle) (part 2) 2 days ago
qwen35-08b-fp32-8k-token-major-home-v5
Add qwen35-08b-fp32-8k-token-major-home-v5 (attention bounded by the used context) (part 2) 2 days ago
qwen35-08b-fp32-8k-token-major-home-v6
Add qwen35-08b-fp32-8k-token-major-home-v6 (column-per-lane gated delta rule) (part 2) 2 days ago
qwen35-08b-fp32-8k-token-major-home
Publish Qwen3.5 0.8B lossless WebTorch bundle (part 2) 28 days ago
qwen35-08b-fp32-int2-g32-mse-home-token-major-v2
Add qwen35-08b-fp32-int2-g32-mse-home-token-major-v2 WebTorch bundle 17 days ago
qwen35-08b-fp32-int2-g32-up-proj-mse-home-token-major-v2
Add qwen35-08b-fp32-int2-g32-up-proj-mse-home-token-major-v2 WebTorch bundle 17 days ago
qwen35-08b-fp32-int8-attn-int4-mlp-gptq-home-token-major-v2-v3
Add qwen35-08b-fp32-int8-attn-int4-mlp-gptq-home-token-major-v2-v3 (fused attention, view elision, packed GEMV, INT8 vocabulary) (part 2) 3 days ago
qwen35-08b-fp32-int8-attn-int4-mlp-gptq-home-token-major-v2-v4
Add qwen35-08b-fp32-int8-attn-int4-mlp-gptq-home-token-major-v2-v4 (tiled prefill GEMM over the v3 bundle) (part 2) 2 days ago
qwen35-08b-fp32-int8-attn-int4-mlp-gptq-home-token-major-v2-v5
Add qwen35-08b-fp32-int8-attn-int4-mlp-gptq-home-token-major-v2-v5 (attention bounded by the used context) (part 2) 2 days ago
qwen35-08b-fp32-int8-attn-int4-mlp-gptq-home-token-major-v2-v6
Add qwen35-08b-fp32-int8-attn-int4-mlp-gptq-home-token-major-v2-v6 (column-per-lane gated delta rule) (part 3) 2 days ago
qwen35-08b-fp32-int8-attn-int4-mlp-gptq-home-token-major-v2
Add qwen35-08b-fp32-int8-attn-int4-mlp-gptq-home-token-major-v2 WebTorch bundle (part 2) 16 days ago
qwen35-08b-fp32-int8-g32-home-token-major-v2-v3
Add qwen35-08b-fp32-int8-g32-home-token-major-v2-v3 (fused attention, view elision, packed GEMV, INT8 vocabulary) (part 2) 3 days ago
qwen35-08b-fp32-int8-g32-home-token-major-v2-v4
Add qwen35-08b-fp32-int8-g32-home-token-major-v2-v4 (tiled prefill GEMM over the v3 bundle) (part 2) 2 days ago
qwen35-08b-fp32-int8-g32-home-token-major-v2-v5
Add qwen35-08b-fp32-int8-g32-home-token-major-v2-v5 (attention bounded by the used context) (part 2) 2 days ago
qwen35-08b-fp32-int8-g32-home-token-major-v2
Publish WebTorch model catalog bundles (part 6) 27 days ago
qwen35-2b-fp16-int4-g8-gptq-up-proj-candidate
Add Qwen3.5-2B mixed FP16 INT4 candidate (part 2) 27 days ago
qwen35-2b-fp32-int8-g32-exclude-l6-l9-l10up-l15o-home-token-major-v2-v3
Add qwen35-2b-fp32-int8-g32-exclude-l6-l9-l10up-l15o-home-token-major-v2-v3 (fused attention, view elision, packed GEMV, INT8 vocabulary) (part 2) 3 days ago
qwen35-2b-fp32-int8-g32-exclude-l6-l9-l10up-l15o-home-token-major-v2-v4
Add qwen35-2b-fp32-int8-g32-exclude-l6-l9-l10up-l15o-home-token-major-v2-v4 (tiled prefill GEMM over the v3 bundle) (part 2) 2 days ago
qwen35-2b-fp32-int8-g32-exclude-l6-l9-l10up-l15o-home-token-major-v2-v5
Add qwen35-2b-fp32-int8-g32-exclude-l6-l9-l10up-l15o-home-token-major-v2-v5 (attention bounded by the used context) (part 2) 2 days ago
qwen35-2b-fp32-int8-g32-exclude-l6-l9-l10up-l15o-home-token-major-v2
Add qwen35-2b-fp32-int8-g32-exclude-l6-l9-l10up-l15o-home-token-major-v2 WebTorch bundle (part 3) 17 days ago
qwen35-2b-fp32-int8-g32-home-token-major-v2
Publish WebTorch model catalog bundles (part 7) 27 days ago
qwen35-2b-multimodal-fp32-three-grid-state-alias-token-major-v2-v3
Add qwen35-2b-multimodal-fp32-three-grid-state-alias-token-major-v2-v3 (fused attention, view elision, packed GEMV) (part 3) 3 days ago
qwen35-2b-multimodal-fp32-three-grid-state-alias-token-major-v2-v4
Add qwen35-2b-multimodal-fp32-three-grid-state-alias-token-major-v2-v4 (tiled prefill GEMM over the v3 bundle) (part 3) 2 days ago
qwen35-2b-multimodal-fp32-three-grid-state-alias-token-major-v2-v5
Add qwen35-2b-multimodal-fp32-three-grid-state-alias-token-major-v2-v5 (attention bounded by the used context) (part 3) 2 days ago
qwen35-2b-multimodal-fp32-three-grid-state-alias-token-major-v2
Publish WebTorch model catalog bundles (part 9) 27 days ago
qwen3vl-instruct-fp32-8k-state-alias-token-major-v2-v3
Add qwen3vl-instruct-fp32-8k-state-alias-token-major-v2-v3 (fused attention, view elision, packed GEMV) (part 2) 3 days ago
qwen3vl-instruct-fp32-8k-state-alias-token-major-v2-v4
Add qwen3vl-instruct-fp32-8k-state-alias-token-major-v2-v4 (tiled prefill GEMM over the v3 bundle) (part 2) 2 days ago
qwen3vl-instruct-fp32-8k-state-alias-token-major-v2-v5
Add qwen3vl-instruct-fp32-8k-state-alias-token-major-v2-v5 (attention bounded by the used context) (part 2) 2 days ago
qwen3vl-instruct-fp32-8k-state-alias-token-major-v2
Publish WebTorch model catalog bundles (part 9) 27 days ago