offload to mmap - #13
Merged
Merged
Conversation
…refine_offload
* allow offload quant * rm cuda * refine and pass test
Refine model_unload behavior to improve robustness and offload precision. - Normalize memory_to_free before logging to avoid None / invalid arithmetic - Make partially_unload more precise by capping memory_to_free to loaded size - Ensure full unload cases are handled correctly after partial unload
- support GDS offload to mmap - support QuantizedTensor offload to mmap - refine mmap offload safety --------- Co-authored-by: ccndcn <2301835860@qq.com> Co-authored-by: FengWen <109639975+ccssu@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
6 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
启动 comfyui 的命令要加上环境变量 MMAP_MEM_THRESHOLD_GB=5，含义是若 cpu mem 小于 5G 时，遇到 offload 会 offload 到 mmap，避免爆 cpu 内存