* env var to change default float to fp16 or bf16
looking for standard names for these. we have FLOAT16 that does something to IMAGE and HALF to convert weights.
working on default bf16 too.
```
RuntimeError: compile failed: <null>(6): error: identifier "__bf16" is undefined
__bf16 cast0 = (nv_bfloat16)(val0);
```
remove that in cifar
* DEFAULT_FLOAT
* default of default
* unit test
* don't check default
* tests work on linux
* init
* removed mulacc
* is uoptimize the problem?
* lol hax make work temporarily fix l8er
* revert extra/ changes
* clean up
* flaky metal tests?
* add back mulacc for metal
* revert last commit
* try skipping linearizer_failure tests
* skip flammit tests... cuz tests all work locally
* try narrow down exact linearizer failure test
* try 2
* try 4
* generated code is the exact same wtf why CI fails
* code for 15 and 17 are exact same with or without mulacc, this should pass
* try only 1 failure
* try garbage collecting lol...
* try del variables lol
* try gcing after del lol...
* is diskcache the problem???
* try disabling opts cache idk
* try remove hack
* try disable github metal cache...
* try CACHELEVEL=0 :D idk anymore
* try increase newCommandQueueWithMaxCommandBufferCount_, im almost out of ideas...
* revert
* actually not a HACK
* oops
* remove cpu and torch backends
* don't copy to cpu
* use clang instead of cpu
* multitensor gathers on the first device
* clang is cpu + use default
* fixup
* bugfix
* lazy rewrite, try 2
* min fix tests
* pass contig test
* put broken pads back
* move that to realize
* no contig child fixes array packing
* so wrong
* now that's correct
* base children
* fix bind issues
* disable to_image_idx
* fix tests
* that failure shouldn't break other tests
* more fixes
* fix torch
* skip failing tests in CI
* 1e-7
* half is broken
* 1e-6 margin of error
* handle reshape of contiguous subparts with explicit mask
* remove the add/remove ones logic in reshape
* accomodate ones in accumulate logic
* make multiply commutative
* fix linting
* make mypy happy
* add test for commutative mul
* merge dimensions in shape_strides for 1 range masks
* add offsets for merging
* fix linting
* add back explicit 1 reshapes
* fix mypy errors
* fix accumulate by includng state
* include non-zero stride dimension in acc
* small cleanup
* more compact to_shape_strides
* more logical cleanup
* compress more
* compress reshape mask
* adding some comments
* small bug fix
* improve test coverage
* remove explicit add remove ones
* small bug in test
* enable test_reshape_splitting_combining
* small fix
* 10 lines less to_shape_strides
* shorten reshape mask
* some more cleanup
* more cleanup
* introduce some symbols for compactness
* more symbols
* more cleaner
* lessen symbols, it became less readable
* remove merge_views from view.reshape
* change to_shape_strides to _merge_dims
* improve readability
* fix corner case
* cleanup
* better handling of 1 <= Variable('i',1,10) & new_dim = Variable('i',1,10)
* rewrite _reshape_mask for readability
* fix white space
* add comment
* nice shorthands for readability
* add proof in docs
* small nit
---------
Co-authored-by: chenyu <chenyu@fastmail.com>
* cpu tests pass
* torch works
* works
* metal works
* fix ops_disk
* metal jit works
* fix openpilot
* llvm and clang work
* fix webgpu
* docs are rly broken
* LRU works on metal
* delete comment
* revert name to ._buf. LRU only on Compiled
* changes
* allocator
* allocator, getting closer
* lru alloc
* LRUAllocator
* all pass
* metal
* cuda
* test examples
* linearizer
* test fixes
* fix custom + clean realize
* fix hip
* skip tests
* fix tests
* fix size=0
* fix MOCKHIP
* fix thneed
* copy better
* simple
* old style metal copy
* fix thneed
* np reshape
* give cuda a device
* var_vals are global
* working with global ish
* better
* fix export model
* fix tests
* better kv cache
* does it run?
* use where for kvmask
* fix excessive var_vals
* fix import
* how does multigpu use this?
* llama kinda work
* faster and simpler
* cleanup
* fix conversation mode
* test cleanups
* fix one more test
* test cleanup
---------
Co-authored-by: George Hotz <geohot@gmail.com>
* move metal+clang to compile api
* all to the new style
* remove binary arg
* fix triton
* fixup tests
* fix clang
* diskcache is generic
* __wrapped__
* compile_gpu
* fix thneed
* keep the src in the ASTRunner
* lib
* move compile_gpu
* compile_gpu in device
* put compiler in astrunner
* test reverts
* triton compiler
* ugh, that too
