github-featured/apache--tvm
2
0
Fork 0
Code Issues Pull Requests Deployments Models Agent Notes Packages Projects Releases Wiki Activity
14,165 Commits 30 Branches 63 Tags
main
Commit Graph

9 Commits

Author SHA1 Message Date
Tianqi Chen 33dcea1686 [REFACTOR][LINT] Modernize ruff config (#18810) 
This PR removes the extra lint violations from the codebase so lint
aligns with the latest style
 2026-02-23 07:29:21 -05:00
Tianqi Chen aa2e609136 [LINT] Modernize lint to use pre-commit hooks (#18807) 
This PR migrates existing lint to use pre-commit hooks
 2026-02-22 11:03:21 -05:00
Tianqi Chen 2030db36e4 [REFACTOR][TARGET] Phase out legacy target string in favor of json (#18785) 
This PR phases out legacy target string format in favor of the json
style format that is more well formed. It also simplfies our overall
code in handling multiple formats.
 2026-02-16 16:21:35 -05:00
Tianqi Chen 2e34d8b04e [REFACTOR][S-TIR] Migrate meta_schedule into s_tir namespace (#18735) 2026-02-08 14:46:37 -05:00
Tianqi Chen d76c729259 [REFACTOR][S-TIR] Initialize the s_tir module (#18712) 
This PR initalizes the s_tir for scheduable TensorIR. The change mainly
starts from python side, the we will gradually move towards the c++ side
in followup PRs. The python main change:

tir.Schedule => s_tir.Schedule
 2026-02-05 09:40:31 -05:00
Tianqi Chen 877b448b02 [REFACTOR][TIR] Rename tir.Block to SBlock (#18689) 
This PR renames tir.Block to SBlock. This clearly indicate the
scheduable property of the block and is a prereq for followup stir
passes refactor.

Main changes:

- Data structure change from Block to SBlock
- Syntax change from T.block to T.sblock
 2026-01-28 08:02:10 -05:00
Siyuan Feng be8e43814a [Refactor] Migrate build API to tvm.compile (#17718) 
* tvm.build -> tvm.compile

* relax.build -> tvm.compile

* update
 2025-03-09 07:23:52 -04:00
Egor Churaev 270c793574 Extend gpu memory bandwidth test to work through RPC (#16608) 
It is possible to measure GPU bandwidth through RPC on an Android
device.
 2024-02-20 10:55:25 +09:00
Junru Shao 592b3583dc [Exec] Add a script to test GPU memory bandwidth (#15287) 
This PR adds a script to test GPU memory bandwidth in TVM. Example
usage:

python -m tvm.exec.gpu_memory_bandwidth \
    "nvidia/geforce-rtx-3090-ti"        \
    --dtype "float32"                   \
    --bx "8,16,32,64,128,256"           \
    --tx "32,64,128,256,512,1024"       \
    --vec "1,2,4"
 2023-07-11 06:26:15 -07:00