vllm-omni

__init__.py

[Model] Add MiniMax H3 diffusion support (#5691 )

2026-08-03 14:10:40 +08:00

test_fasth3_checkpoint.py

[Diffusion][Model] Add direct FastH3 8-Step V2 checkpoint loading (#7610 )

2026-09-17 08:41:52 +00:00

test_minimax_h3_collectives.py

[Bugfix][MiniMax-H3] Keep keyframe VAE encoding rank-local

2026-09-18 01:20:13 +00:00

test_minimax_h3_contract.py

Merge commit '6fe1ff7709c72c08bbfc33a7e14b73ec94135549' into codex-issue-7035-h100-determinism

2026-09-17 09:22:22 +00:00

test_minimax_h3_dlo_lifecycle.py

[diffusion][feature] Add component-selective offload policies (#5929 )

2026-09-06 05:40:09 +08:00

test_minimax_h3_e2e.py

[MiniMax-H3] TeaCache support and Cache-DiT validation (#5840 )

2026-08-09 15:07:21 +00:00

test_minimax_h3_encoder_sdpa.py

[Bugfix] Scope MiniMax-H3 cuDNN SDPA state (#6710 )

2026-08-28 19:40:50 -07:00

test_minimax_h3_execution_modes.py

[feat] Extend disaggregated MiniMax-H3 stage with VAE encoders (#6939 )

2026-09-16 16:52:35 +08:00

test_minimax_h3_fasth3.py

[Diffusion][Model] Add direct FastH3 8-Step V2 checkpoint loading (#7610 )

2026-09-17 08:41:52 +00:00

test_minimax_h3_lora.py

[Feature][MiniMax-H3] Support the full LightX2V Turbo LoRA matrix (#7062 )

2026-09-06 20:23:36 +08:00

test_minimax_h3_modulation.py

[Attention] [P1] Keep H3 VSA policy in the model and share sparse primitives (#7535 )

2026-09-16 15:47:31 +08:00

test_minimax_h3_native_lora.py

[Feature][MiniMax-H3] Support the full LightX2V Turbo LoRA matrix (#7062 )

2026-09-06 20:23:36 +08:00

test_minimax_h3_offload.py

[feat] Extend disaggregated MiniMax-H3 stage with VAE encoders (#6939 )

2026-09-16 16:52:35 +08:00

test_minimax_h3_packing.py

[Model][MiniMax-H3] Multi-GPU serving fixes and layer-wise offload component selection (#7047 )

2026-09-14 10:02:30 -07:00

test_minimax_h3_parallel.py

[Feature][MiniMax-H3] Complete VSA and Ulysses support (#6909 )

2026-09-02 07:19:21 -04:00

test_minimax_h3_quality_policy.py

[Model][Feat] Support Minimax-H3 quality grading requests through dynamic loading/unloading with Cache-DiT (#5853 )

2026-08-07 09:07:23 +00:00

test_minimax_h3_quantization_quality.py

[Diffusion][Model] Add direct FastH3 8-Step V2 checkpoint loading (#7610 )

2026-09-17 08:41:52 +00:00

test_minimax_h3_quantization.py

[Diffusion][Model] Add direct FastH3 8-Step V2 checkpoint loading (#7610 )

2026-09-17 08:41:52 +00:00

test_minimax_h3_qwen3vl_gqa.py

[Perf][NPU] Enable native GQA & fused AddNorm for MiniMax-H3 encoder (#6040 )

2026-08-26 09:14:05 +08:00

test_minimax_h3_qwen3vl_rope.py

[Perf][NPU] Enable native GQA & fused AddNorm for MiniMax-H3 encoder (#6040 )

2026-08-26 09:14:05 +08:00

test_minimax_h3_qwen3vl_swiglu.py

[Bugfix][NPU] Fix MiniMax-H3 INT8 quantization dispatch (#6876 )

2026-09-07 14:50:44 +00:00

test_minimax_h3_rmsnorm.py

[Perf][NPU] Enable native GQA & fused AddNorm for MiniMax-H3 encoder (#6040 )

2026-08-26 09:14:05 +08:00

test_minimax_h3_step_execution.py

[feat] Extend disaggregated MiniMax-H3 stage with VAE encoders (#6939 )

2026-09-16 16:52:35 +08:00

test_minimax_h3_turbo_matrix.py

[Feature][MiniMax-H3] Support the full LightX2V Turbo LoRA matrix (#7062 )

2026-09-06 20:23:36 +08:00

test_minimax_h3_vae_chunks.py

[2/N] Add a minimal temporal chunk callback for MiniMax-H3 (#7017 )

2026-09-09 16:40:32 +08:00

test_minimax_h3_vae_gather_reuse.py

[Model][MiniMax-H3] Multi-GPU serving fixes and layer-wise offload component selection (#7047 )

2026-09-14 10:02:30 -07:00

test_minimax_h3_vae_ops.py

[Model][MiniMax-H3] Multi-GPU serving fixes and layer-wise offload component selection (#7047 )

2026-09-14 10:02:30 -07:00

test_minimax_h3_vae_tiling.py

[BugFix][Diffusion] Fix MiniMax-H3 VAE hang when decoder tiles are fewer than ranks (#6345 )

2026-08-20 12:42:14 +08:00

test_vsa_layout.py

[Attention] [P1] Keep H3 VSA policy in the model and share sparse primitives (#7535 )

2026-09-16 15:47:31 +08:00