Currently, the parameters I am using is as follows: <div class="highlight highligh

The use of tune_relax can be something like <div

After finishing tuning, I use: <div class="highlight highlight-source-python notra

Hi <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="

Thanks <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-u

[MetaSchedule] [CUDA target] Did you forget to bind? about web-stable-diffusion HOT 8 CLOSED

mlc-ai commented on May 19, 2024 1

[MetaSchedule] [CUDA target] Did you forget to bind?

from web-stable-diffusion.

Comments (8)

MasterJH5574 commented on May 19, 2024 1

The use of tune_relax can be something like

ms.relax_integration.tune_relax(
    mod=mod_deploy,
    target=tvm.target.Target("apple/m1-gpu-restricted"),  # for WebGPU 256-thread limitation
    params={},
    builder=ms.builder.LocalBuilder(
        max_workers=os.cpu_count(),
    ),
    runner=ms.runner.LocalRunner(timeout_sec=60),
    work_dir="log_db",
    max_trials_global=50000,
    max_trials_per_task=2000,
)

from web-stable-diffusion.

Civitasv commented on May 19, 2024

After finishing tuning, I use:

with args.target, db, tvm.transform.PassContext(opt_level=3):
        mod_deploy = relax.transform.MetaScheduleApplyDatabase(enable_warning=True)(mod)

It will show many warnings like:

[17:27:57] /home/wyc/husen/sandbox/tvm/src/relax/transform/meta_schedule.cc:162: Warning: Tuning record is not found for primfunc: matmul23
[17:27:57] /home/wyc/husen/sandbox/tvm/src/relax/transform/meta_schedule.cc:162: Warning: Tuning record is not found for primfunc: fused_conv2d14_add24_add25
[17:27:57] /home/wyc/husen/sandbox/tvm/src/relax/transform/meta_schedule.cc:162: Warning: Tuning record is not found for primfunc: take
[17:27:57] /home/wyc/husen/sandbox/tvm/src/relax/transform/meta_schedule.cc:162: Warning: Tuning record is not found for primfunc: fused_conv2d37_add34_add35_divide7
[17:27:57] /home/wyc/husen/sandbox/tvm/src/relax/transform/meta_schedule.cc:162: Warning: Tuning record is not found for primfunc: fused_conv2d24_add10
[17:27:57] /home/wyc/husen/sandbox/tvm/src/relax/transform/meta_schedule.cc:162: Warning: Tuning record is not found for primfunc: fused_conv2d7_add10
[17:27:57] /home/wyc/husen/sandbox/tvm/src/relax/transform/meta_schedule.cc:162: Warning: Tuning record is not found for primfunc: fused_matmul28_add27_add28
[17:27:57] /home/wyc/husen/sandbox/tvm/src/relax/transform/meta_schedule.cc:162: Warning: Tuning record is not found for primfunc: fused_matmul11_add11_strided_slice4
[17:27:57] /home/wyc/husen/sandbox/tvm/src/relax/transform/meta_schedule.cc:162: Warning: Tuning record is not found for primfunc: fused_conv2d4_add10_add12
[17:27:57] /home/wyc/husen/sandbox/tvm/src/relax/transform/meta_schedule.cc:162: Warning: Tuning record is not found for primfunc: fused_matmul9_add8_gelu

Then I use relax.build, it will show the typical Did you forget to bind? error.

I don't know why this happen.

cc @tqchen @MasterJH5574

from web-stable-diffusion.

nineis7 commented on May 19, 2024

You can use diffusers==0.15.0 version and problems may all be solved. ^^

from web-stable-diffusion.

Civitasv commented on May 19, 2024

You can use diffusers==0.15.0 version and problems may all be solved. ^^

Thanks for your help! But I've tried this, still not work.

from web-stable-diffusion.

MasterJH5574 commented on May 19, 2024

Hi @Civitasv, thanks for the question! We used meta_schedule.relax_integration.tune_relax to tune the IRModule mod_deploy.

I guess the mismatch you observed is because both the TIR extraction of tune_relax and MetaScheduleApplyDatabase will “normalize” each TIR function, while tune_tir does not. You can try tune_relax and see if it works for your case.

from web-stable-diffusion.

Civitasv commented on May 19, 2024

Thanks for your reply.
I've tried this, but sadly, it still cannot work. Following your advice, I've changed my configuration as follows:

def do_all_tune(mod, target):
    tunning_dir = "gpu3090_workdir"
    tunning_record = "gpu3090/database_tuning_record.json"
    tunning_workload = "gpu3090/database_workload.json"
    cooldown_interval = 0
    trial_cnt = 100
    trial_per = 2

    local_runner = ms.runner.LocalRunner(cooldown_sec=cooldown_interval, timeout_sec=60)
    database = ms.relax_integration.tune_relax(
        mod=mod,
        target=target,
        work_dir=tunning_dir,
        max_trials_global=trial_cnt,
        max_trials_per_task=trial_per,
        runner=local_runner,
        params={},
    )
    if os.path.exists(tunning_record):
        os.remove(tunning_record)
    if os.path.exists(tunning_workload):
        os.remove(tunning_workload)
    database.dump_pruned(
        ms.database.JSONDatabase(
            path_workload=tunning_workload,
            path_tuning_record=tunning_record,
        )
    )

Still saying #43 (comment).

I wonder if it is relavent to the max_trials_global and max_trials_per_task option.

from web-stable-diffusion.

Civitasv commented on May 19, 2024

I wonder if it is relevent to the max_trials_global and max_trials_per_task option.

Yes, it is relevant. For 10000 and 2000 for trial_cnt and trial_per, only the take operator is wrong.

from web-stable-diffusion.

MasterJH5574 commented on May 19, 2024

Thanks @Civitasv! Glad that it works :-)

from web-stable-diffusion.

[MetaSchedule] [CUDA target] Did you forget to bind? about web-stable-diffusion HOT 8 CLOSED

Comments (8)

Related Issues (20)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent