* this
* clean up
* more clean ups and improve debug msg
* more correct training toggler
* remove manual training toggling
* change some variable names
* actually just add the training toggle for LIMIT envvar too
* more refinement
* __call__ and OnnxRunner
* fix half pylint, other half is importing from onnx while this file is onnx.py, figure out later
* ahhhh found another mistake
* remove limit from __call__
---------
Co-authored-by: chenyu <chenyu@fastmail.com>
* is 67% considered fixed?
* move test up
* share function
* add qgemm too
* make sure qgemm comes out as int
* actually that note is not right
* remove qgemm (I did it wrong) and add it later lol.
* QLinearEverything
* ok ort verify passes
* this should be int instead
* cast to int then char to do wraparound
* cleaner
* move contrib ops to microsoft ops
---------
Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
* validate variable dims and fix buffer_parse to not use numpy
* fix var_dim parsing
* gah float16
* revert buffer_parse stuff
* revert that revert
* correct some err msges
* add some more debug msgs I find helpful
* tensor init noop
* add an assert just for the sake of it.
---------
Co-authored-by: chenyu <chenyu@fastmail.com>
* implemented in tensor
* apply onnx tests to asymmetrical pads
* better onnx op ordering
* correct ceil_mode asymmetrical
* fix onnx_ops comments
* a few more TODOs and fix some stupidity
* fix some typing
* fix test
* mypy still a little messed up
* refactor out pad struct transformation
* add simple docs for now
* add whatever tests possible
* add tests for _resolve_pool_pads
* better err msg
* whoops didn't mean to include this
* retry CI
* enable asymmetric pads onnx tests
* better docs
---------
Co-authored-by: chenyu <chenyu@fastmail.com>
* connect to gpu
* rlc init?
* gfx comp start init
* early init is hardoded, some progress with fw
* gart
* progress, next mqd
* ring setup, still does not execute anything
* ugh write correct reg
* pci2: vm
* pci2: start psp
* vm seems to work
* pci2: gfx start
* pci2: fix psp ring resp
* pci2: try ring
* pci2: mes and some fixes
* pci2: some progress
* pci2: progress
* pci2: mm
* pci2: discovery
* pci2: correct apertures
* pci2: b
* pci2: i
* pci2: l
* pci2: o
* pci2: cmu
* pci2: mes_kiq works
* pci2: mes
* pci2: kcq does not work(
* pci2: unhalt gfx
* ops_am
* minor
* check if amdgpu is there, or we will crash
* bring back graph, it just works
* less prints
* do not init mes (not used)
* remove unused files
* ops_am: start move into core
* ops_am: works
* clcks, but still slower
* faster + no mes_kiq
* vm frags + remove mes
* cleanup fw
* gmc tiny cleanup
* move to ops_amd
* comment out what we dont really need
* driverless
* close in speed
* am clean most of ips
* gmc to ips
* cleaner
* new vm walker
* comment old one
* remove unsued autogens
* last write ups
* remove psp hardcoded values
* more
* add logs
* ih
* p2p and sdma
* vfio hal and interrupts
* smth
* amd dev iface
* minor after rebase
* bind for sdma
* Revert "bind for sdma"
This reverts commit a90766514d.
* tmp
* debug new mm
* ugh, allreduce hangs fixed
* p1
* works
* no pci.py
* cleaner a bit
* smth
* tiny cleanups
* cleaner a bit
* pciiface
* linter
* linter 2
* linter 3
* linter
* pylint
* reverted unrelated changes
* unrelated
* cmp tool
* ugh wrong fw
* clockgating
* unrelated
* alloc smaller chunks
* this
* opt sigs
* collect stat
* ops
* upd
* proclogs
* proclogs2
* vfio
* ruff
* linter pylint
* oops
* mypy p1
* mem fix
* mypy p2
* mypy p3
* mypy p4
* correct
* minor
* more tests
* linter in tests
* pci_regs header
* minor write up
* setup
* do not require libs
---------
Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
it's a python style mod. possibily can be cleaner with a floor div
relaxed the vmin for MOD slightly for cstyle negatives mod, it's more correct and might fix other bugs
* validate that FC exists before loading pretrained weights
* add test case for ResNet pretrained model without FC layer
* remove extra newline
* rename test case
* reraise exception if not handled by check
* implemented
* this implementation is now correct
* this is fine I guess
* better variable names
* finally correct gathernd
* add a note
* eh just leave it at this for now
* teeny adjustment
* move to_python_const out
* move more over
* try deleting alternative gather implementation
* Revert "try deleting alternative gather implementation"
This reverts commit d46b30b717.
* add types to onnx ops
* better debug msg
* improve some com.microsoft too
---------
Co-authored-by: chenyu <chenyu@fastmail.com>
* assign early folding [pr]
* move to to_si
* -
* fix generate_dataset
* diff too big
* no recreation, no diff
* gzip
* new sops from tiny10
* final try
* 1 is simpler than 2
* variable name
* change error wording
* shapes for sequence type must be homogeneous
* bug fix for model benchmark
* fix comments too
---------
Co-authored-by: chenyu <chenyu@fastmail.com>
* feelsbadman
* feelsextrabadman
* make sure indices is on same device as self Tensor
* renamed to _one_hot_along_dim
* revert onnx change will do them in onnx only PRs
* address feedback
* add onnx changes here too
* make pad arg better
* revert pad arg
* maybe still keep dim
* simplify onehot onnx ops more
---------
Co-authored-by: chenyu <chenyu@fastmail.com>
* start
* simplify ops
* why did this not work before
* will split buffer parse to separate pr
* flip the error order
* only this much for now
* to_python_const clean up
* minimize diff
* move tensor_methods into onnx.py
* improve some type signatures
---------
Co-authored-by: chenyu <chenyu@fastmail.com>
* simple clean ups first
* more work
* kinda have adam
* ooo momentum worked nicely
* almost there
* wow.. is the onnx test wrong
* nicer optim stuff
* just skip that test
* small comment changes
* use naming convention from other parts of codebase
---------
Co-authored-by: chenyu <chenyu@fastmail.com>
