Skip to content

Actions: onnxruntime/mobius

Actions

Benchmark

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
benchmark.yml
2,500+ workflow runs
2,500+ workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
fix(deepseek-v4): per-layer CSA/HCA compressed-record symbolic dim Benchmark #2650: Pull request #622 opened by justinchuby
1m 51s deckard/csa-per-layer-record-axis
deckard/csa-per-layer-record-axis
1m 51s
Fix real PLaMo2 cached decode parity Benchmark #2649: Pull request #620 synchronize by justinchuby
1m 55s justinchuby-fix-plamo2-runtime-parity
justinchuby-fix-plamo2-runtime-parity
1m 55s
Add dedicated Kimi-K3 GGUF support Benchmark #2648: Pull request #621 opened by justinchuby
1m 48s justinchuby-kimi-k3-gguf
justinchuby-kimi-k3-gguf
1m 48s
Fix real PLaMo2 cached decode parity Benchmark #2647: Pull request #620 opened by justinchuby
1m 54s justinchuby-fix-plamo2-runtime-parity
justinchuby-fix-plamo2-runtime-parity
1m 54s
Add dedicated Kimi Linear GGUF support Benchmark #2646: Pull request #619 opened by justinchuby
1m 42s justinchuby-kimi-linear-gguf
justinchuby-kimi-linear-gguf
1m 42s
Add ORT GenAI end-to-end CI Benchmark #2645: Pull request #618 opened by justinchuby
1m 53s justinchuby-ort-genai-e2e-ci
justinchuby-ort-genai-e2e-ci
1m 53s
Validate real PLaMo2 GGUF import Benchmark #2644: Pull request #617 opened by justinchuby
1m 48s justinchuby-validate-real-plamo2
justinchuby-validate-real-plamo2
1m 48s
Add exact MiniMax-01 GGUF support Benchmark #2643: Pull request #616 opened by justinchuby
1m 57s justinchuby-minimax-01-gguf
justinchuby-minimax-01-gguf
1m 57s
Add GraniteHybrid routed-MoE GGUF support Benchmark #2642: Pull request #615 opened by justinchuby
1m 50s justinchuby-granitehybrid-moe-gguf
justinchuby-granitehybrid-moe-gguf
1m 50s
Add Nemotron-H MoE GGUF support Benchmark #2641: Pull request #614 opened by justinchuby
1m 58s justinchuby-complete-nemotron-h-moe-gguf
justinchuby-complete-nemotron-h-moe-gguf
1m 58s
Add full Jamba GGUF MoE support Benchmark #2640: Pull request #613 opened by justinchuby
1m 46s justinchuby-complete-jamba-gguf
justinchuby-complete-jamba-gguf
1m 46s
Add dedicated PLaMo2 model and GGUF import Benchmark #2639: Pull request #612 opened by justinchuby
1m 53s justinchuby-plamo2-gguf
justinchuby-plamo2-gguf
1m 53s
Generate graph-driven ORT GenAI decoder configs Benchmark #2638: Pull request #611 opened by justinchuby
1m 50s justinchuby-generic-genai-configs
justinchuby-generic-genai-configs
1m 50s
Fail closed on lossy GGUF quantization preservation Benchmark #2637: Pull request #609 synchronize by justinchuby
1m 49s justinchuby-fix-gguf-q4-parity
justinchuby-fix-gguf-q4-parity
1m 49s
Add dedicated Falcon-H1 model and GGUF import Benchmark #2636: Pull request #610 opened by justinchuby
1m 47s justinchuby-falcon-h1-gguf
justinchuby-falcon-h1-gguf
1m 47s
Fail closed on lossy GGUF quantization preservation Benchmark #2635: Pull request #609 opened by justinchuby
1m 54s justinchuby-fix-gguf-q4-parity
justinchuby-fix-gguf-q4-parity
1m 54s
Materialize exact GGUF tokenizers Benchmark #2634: Pull request #608 opened by justinchuby
1m 49s justinchuby-materialize-gguf-tokenizers
justinchuby-materialize-gguf-tokenizers
1m 49s
Add small-model GGUF runtime evidence Benchmark #2633: Pull request #607 opened by justinchuby
1m 51s justinchuby-validate-small-gguf-models
justinchuby-validate-small-gguf-models
1m 51s
Add dedicated LFM2MoE GGUF graph support Benchmark #2632: Pull request #606 opened by justinchuby
1m 46s justinchuby-implement-deferred-recurrent-gguf
justinchuby-implement-deferred-recurrent-gguf
1m 46s
feat(deepseek-v4): default-off native CompressedSparseAttention (HCA ratio-128) export [C1, DRAFT] Benchmark #2631: Pull request #593 synchronize by justinchuby
1m 46s deckard/deepseek-v4-csa-hca-c1
deckard/deepseek-v4-csa-hca-c1
1m 46s
Finalize generated GGUF support matrix Benchmark #2630: Pull request #604 opened by justinchuby
1m 44s justinchuby-finalize-gguf-support-matrix
justinchuby-finalize-gguf-support-matrix
1m 44s
Add opt-in --paged-attention export for dense MLA (LATENT PagedAttention) [Slice 3B] Benchmark #2629: Pull request #599 synchronize by justinchuby
1m 41s squad/mobius-3b-paged-attention-export
squad/mobius-3b-paged-attention-export
1m 41s
Add opt-in --paged-attention export for dense MLA (LATENT PagedAttention) [Slice 3B] Benchmark #2628: Pull request #599 synchronize by justinchuby
1m 48s squad/mobius-3b-paged-attention-export
squad/mobius-3b-paged-attention-export
1m 48s
Fix Olive-quantized Qwen3 MoE export Benchmark #2627: Pull request #525 synchronize by titaiwangms
1m 43s fix/moe-packed-fused-expert-weights
fix/moe-packed-fused-expert-weights
1m 43s
Add opt-in --paged-attention export for dense MLA (LATENT PagedAttention) [Slice 3B] Benchmark #2626: Pull request #599 synchronize by justinchuby
1m 39s squad/mobius-3b-paged-attention-export
squad/mobius-3b-paged-attention-export
1m 39s