Skip to content

update ar models #1110

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
gushiqiao wants to merge 1 commit into
base: main
Choose a base branch
from
+196 −3,194
Open

update ar models #1110

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 0 additions & 34 deletions configs/lingbot_fast/kv_calib/lingbot_fast_i2v_kv_sagequant_calib.json
View file
Open in desktop

This file was deleted.

34 changes: 0 additions & 34 deletions configs/lingbot_fast/kv_calib/lingbot_fast_i2v_kv_turboquant_calib.json
View file
Open in desktop

This file was deleted.

2 changes: 1 addition & 1 deletion configs/lingbot_fast/lingbot_fast_i2v.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
"t5_cpu_offload": false,
"vae_cpu_offload": false,
"use_image_encoder": false,
"dit_original_ckpt": "path/to/lingbot_world_fast/",
"dit_original_ckpt": "/data/nvme4/models/lingbot-world-base-cam/lingbot_world_fast",
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot Jun 2, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

Avoid hardcoding absolute, user-specific local paths (e.g., /data/nvme4/gushiqiao/...) in shared configuration files. This makes the configuration non-portable and will fail on other environments. Consider using a relative path or a placeholder/environment variable instead.

"ar_config": {
"local_attn_size": 21,
"num_frame_per_chunk": 3,
Expand Down
34 changes: 0 additions & 34 deletions configs/lingbot_fast/lingbot_fast_i2v_kv_sagequant.json
View file
Open in desktop

This file was deleted.

34 changes: 0 additions & 34 deletions configs/lingbot_fast/lingbot_fast_i2v_kv_turboquant.json
View file
Open in desktop

This file was deleted.

2 changes: 1 addition & 1 deletion configs/matrix_game2/matrix_game2_universal.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
"local_attn_size": 6,
"num_frame_per_chunk": 3,
"denoising_step_list": [1000.0, 908.8427, 713.9794],
"kv_offload": true
"kv_offload": false
},
"sub_model_folder": "base_distilled_model",
"sub_model_name": "base_distill.safetensors",
Expand Down
4 changes: 2 additions & 2 deletions configs/seko_talk/ar/seko_talk_ar.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@
"step_kv_cache": true,
"sink_size": 2,
"local_attn_size": 21,
"kv_offload": false,
"async_vae_decode": true
"kv_offload": true,
"async_vae_decode": false
}
}
12 changes: 4 additions & 8 deletions configs/seko_talk/ar/seko_talk_ar_kv_dist.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,11 +17,11 @@
"offload_granularity": "block",
"use_31_block": true,
"dit_quantized": true,
"dit_quantized_ckpt": "/models/seko_ar/converted_fp8.safetensors",
"dit_quantized_ckpt": "/data/nvme5/gushiqiao/models/SekoTalk-Distill-AR/converted_fp8.safetensors",
"dit_quant_scheme": "fp8-sgl",
"adapter_quantized": true,
"adapter_quant_scheme": "fp8",
"adapter_model_path": "/models/seko_ar/-audio_adapter_fp8.pt",
"adapter_model_path": "/data/nvme5/gushiqiao/models/SekoTalk-Distill-AR/-audio_adapter_fp8.pt",
Comment on lines +20 to +24
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot Jun 2, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

Avoid hardcoding absolute, user-specific local paths (e.g., /data/nvme5/gushiqiao/...) in shared configuration files. This makes the configuration non-portable and will fail on other environments. Consider using relative paths or placeholders/environment variables instead.

"audio_feature_dim": 1024,
"audio_projection_dim": 1024,
"audio_num_tokens": 32,
Expand All @@ -30,16 +30,12 @@
"look_ahead": 0.0,
"audio_feat_window_neighbor_frame": 0,
"audio_feat_fps": 50,
"parallel": {
"seq_p_size": 8,
"seq_p_attn_type": "ulysses"
},
"ar_config": {
"num_frame_per_chunk": 1,
"step_kv_cache": true,
"sink_size": 2,
"local_attn_size": 21,
"kv_offload": false,
"async_vae_decode": true
"kv_offload": true,
"async_vae_decode": false
}
}
8 changes: 1 addition & 7 deletions configs/seko_talk/ar/seko_talk_ar_kv_kiviquant.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,12 +36,6 @@
"sink_size": 2,
"local_attn_size": 21,
"kv_offload": true,
"async_vae_decode": true,
"kv_quant": {
"quant_scheme": "kivi",
"k_cache_type": "int4",
"v_cache_type": "int4",
"group_size": 64
}
"async_vae_decode": true
}
}
46 changes: 0 additions & 46 deletions configs/seko_talk/ar/seko_talk_ar_kv_longlivequant.json
View file
Open in desktop

This file was deleted.

29 changes: 0 additions & 29 deletions configs/self_forcing/kv_calib/wan_t2v_sf_sagequant_calib.json
View file
Open in desktop

This file was deleted.

29 changes: 0 additions & 29 deletions configs/self_forcing/kv_calib/wan_t2v_sf_sagequant_calib_14b.json
View file
Open in desktop

This file was deleted.

29 changes: 0 additions & 29 deletions configs/self_forcing/kv_calib/wan_t2v_sf_turboquant_calib.json
View file
Open in desktop

This file was deleted.

29 changes: 0 additions & 29 deletions configs/self_forcing/kv_calib/wan_t2v_sf_turboquant_calib_14b.json
View file
Open in desktop

This file was deleted.

Loading
Loading