 Copilotandsooxt98
|
3e4011f7d2
|
Document SageAttention backend for 2x inference speedup (#7)
* Initial plan
* Update README with SageAttention documentation
Co-authored-by: sooxt98 <13378059+sooxt98@users.noreply.github.com>
* Improve README clarity based on code review feedback
Co-authored-by: sooxt98 <13378059+sooxt98@users.noreply.github.com>
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: sooxt98 <13378059+sooxt98@users.noreply.github.com>
|
2025-12-10 11:38:53 +08:00 |
|
|
sooxt98
|
a2dddaf542
|
Sage attention speed boost
Added attention_backend parameter to execute method and integrated SageAttention support.
|
2025-12-10 11:32:39 +08:00 |
|
|
|
11221ba21a
|
Add pyproject.toml for Custom Node Registry (#3)
* chore(pyproject): Add pyproject.toml for Custom Node Registry
* Update PublisherId in pyproject.toml
---------
Co-authored-by: async () = process.env.GIT_USERNAME || (await ghUser()).email && (await ghUser()).name || DIE("Missing env.GIT_USERNAME") <async () = process.env.GIT_USEREMAIL || (await ghUser()).email && (await ghUser()).email || DIE("Missing env.GIT_USEREMAIL")>
Co-authored-by: sooxt98 <sooxiaotong@gmail.com>
|
2025-12-09 17:11:26 +08:00 |
|
|
Robin Huangandasync () = process.env.GIT_USERNAME || (await ghUser()).email && (await ghUser()).name || DIE("Missing env.GIT_USERNAME")
|
06ae6c019b
|
chore(publish): Add Github Action for Publishing to Comfy Registry (#2)
Co-authored-by: async () = process.env.GIT_USERNAME || (await ghUser()).email && (await ghUser()).name || DIE("Missing env.GIT_USERNAME") <async () = process.env.GIT_USEREMAIL || (await ghUser()).email && (await ghUser()).email || DIE("Missing env.GIT_USEREMAIL")>
|
2025-12-09 17:09:15 +08:00 |
|
|
|
b6d27c34c7
|
Add CPU offload support for low VRAM GPUs (#1)
* Initial plan
* Implement low VRAM support with CPU offload option
Co-authored-by: sooxt98 <13378059+sooxt98@users.noreply.github.com>
* Address code review feedback - fix grammar and consistency
Co-authored-by: sooxt98 <13378059+sooxt98@users.noreply.github.com>
* Change default CPU offload setting to true
Updated the default value for 'enable_cpu_offload' to 'true' and adjusted the CPU offload logic for the transformer model loading process.
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: sooxt98 <13378059+sooxt98@users.noreply.github.com>
Co-authored-by: sooxt98 <sooxiaotong@gmail.com>
|
2025-12-08 20:22:35 +08:00 |
|
|
Sheldon Soo
|
a06e82b411
|
init
|
2025-12-06 20:45:57 +08:00 |
|