* add kernelize
* remove that
* kernelize returns self
* update abstractions2.py
* kernelize in test_schedule
* temp: assert BUFFER_VIEW's existence
* ASSIGN must have a buffer or subbuffer target
* assert and shrink
* fix
* padded setitem
* var
* toposort once
* extra
* base_buffer
* end with BUFFER_VIEW
* setitem for disk
* test_setitem_becomes_subbuffer
* mul slice test
* torch backend fix 1
* non-deterministic
* keep subbuffer
* random speedups [pr]
* speeding up linearizer
* test_gemm passes
* progress
* test_gemm passes
* working
* simpler
* blockstart unneeded
* simpler
* bugfix
* work
* don't compare
* faster
* progress
* cleanups
* work
* cleanups
* working
* reorder
* name is dumb
* fix tests
* lin2 works
* clean ctx
* mostly bottom up
* passes
* same speed now
* new lin is faster
* dedup
* lines and tuples
* track that
* lin
* revert that
* tests should pass
* merge siblings
* cleaner expression
* only lin2
* finally, some speed
* simpler
* fix unmergables with blockends
* set pad t 3 for amd padded tc test
* change pad for amd regardless CI
* test tc padded uops and correctness separately
* add test_tensor_cores_padded_uops test to ci
* remove redundant chack for amd device
* cleanup
* Kernel.apply_opts [pr]
updated all `for opt in`. also updated a few test_liinearizer tests to not implcitly depend on hand_coded_optimization
* not you yet
* Add amax support to Tensor operations
- Implemented amax function in backend.py for tensor max operations.
- Added unit tests for amax in test.py to ensure correct functionality.
* Fix formatting in amax output function
- Adjusted spacing in the amax output lambda function in backend.py
- Improved code readability for better maintenance
Not-quite-required but makes cloud graph a *lot* cleaner because unlike
raw compiled programs `GraphRunner` takes `Buffer`s like other runners.
Otherwise either of: adding a new option to not free on `__del__`,
(ab)using `external_ptr` to prevent free, or making something like a
`FakeBuffer` is required.
* fp8s part 1
* prettier
* fixes
* fixes
* remove stuff that should be in next pr
* revert
* add creation
---------
Co-authored-by: pkotzbach <[email protected]>
* FastPatternMatcher
* works without that
* fix test pickle
* strict len
* compile match function
* dynamic compile
* fast
* faster
* compile
* track
* a lot faster
* clean up
* dup or
* faster and simpler
* fast match doesn't support store
* plane
* minor refactor
* real speed
* don't imply return None
* upat
* fix test
* heard you wanted more speed
* no generator
* split cf
* early fixup
* fxn fixup
* reconstruct_function
* Revert "reconstruct_function"
This reverts commit 37dac010ab.
* simpler stuff
* too big
* upat compile error
* cleanups
* don't cache that
* cleanups
* 10 -> 15
geohot