a82db2d331
Revert "Filet o Fish model" ( #34780 )
...
Revert "Filet o Fish model (#34775 )"
This reverts commit 31076b818d
2025-03-05 01:41:16 -08:00
31076b818d
Filet o Fish model ( #34775 )
...
* 690b01c3 seems ok
* correct temporal
* push
* inplace
* bs
* what thw
* is this wrong
* frames are skipped
* new models
* simplify decimation
* clean up
* clean up modelframe
* need attr
* lint
* 0
* use all samples
* this should break - Revert "use all samples"
This reverts commit 6c0d7943ac5fbb7ae60af1a1201e2423e4c3c105.
* add lc probs
* Revert "this should break - Revert "use all samples""
This reverts commit ca38c54333555266a0d2c885c28af28941841431.
* Reapply "this should break - Revert "use all samples""
This reverts commit a3f0246f209f85f06b9090d9492bfba32ed8cfed.
* Revert "Reapply "this should break - Revert "use all samples"""
This reverts commit 7fd3d2a191b688e5ef7b4dcc8f5379e900af10f8.
---------
Co-authored-by: Comma Device <device@comma.ai >
2025-03-04 20:35:57 -08:00
e5ba737db0
Revert "Filet o Fish model ( #34637 )"
...
This reverts commit 159b1c9eb4
2025-03-03 22:56:59 -08:00
159b1c9eb4
Filet o Fish model ( #34637 )
...
* 690b01c3 seems ok
* correct temporal
* push
* inplace
* bs
* what thw
* is this wrong
* frames are skipped
* new models
* simplify decimation
* clean up
* clean up modelframe
* need attr
* lint
* 0
---------
Co-authored-by: Comma Device <device@comma.ai >
2025-03-03 15:15:36 -08:00
29ca4aa7de
modeld refactor: supercombo -> vision+policy ( #34718 )
...
* should be ok
* update tg
* type
* wrong model
* is no more
* update readme
* add back
---------
Co-authored-by: Comma Device <device@comma.ai >
2025-02-27 17:00:56 -08:00
2eb3585dae
Not Too Shabby Model ( #34484 )
...
* b25c27a8-263b-4f3f-b1f8-72ac49b4f9c7/700
* replay
* model_replay: support empty
2025-01-28 12:16:13 -08:00
1068779294
modeld: properly release OpenCL context in __dealloc__ method ( #34353 )
...
release OpenCL context in __dealloc__
2025-01-12 10:15:26 -08:00
c8264cbf2c
Notre Dame model in tinygrad ( #34324 )
...
* release model: 6f23a03f-486b-4d3e-a314-19d149644c7c/700
* old style model in tinygrad
* fix desire
* tg hack
* 20Hz
* no gas probs
* No gas here
* better indexing
---------
Co-authored-by: Yassine Yousfi <yyousfi1@binghamton.edu >
2025-01-06 20:52:36 -08:00
1a7c284445
National Public Radio Model 📻 ( #34259 )
...
* f3a009b7-dcb9-41f3-8917-6fcb3cec37bf/400
* 65f26b40-56c9-4c6c-a3ac-e1788bd52567/400
2024-12-18 16:13:47 -08:00
17ca6389e1
Tinygrad runner ( #34261 )
...
* squash
* dmonitoringmodeld: use cl transform (#34235 )
* needs cleanup
* only if tici
* bump tinygrad
* check width
* base modelframe
* .
* need to be args
* more cleanup
* no _frame in base
* tici only
* its DrivingModelFrame
* .6 is fair
---------
Co-authored-by: Comma Device <device@comma.ai >
* Update tinygrad
* tg upstream
* bump tg
* bump tg
* debug
* attr
* misc cleanup
* whitespace
* remove
* Add TODOs to make python proc for modelrunners
* whitespace
---------
Co-authored-by: ZwX1616 <zwx1616@gmail.com >
Co-authored-by: Comma Device <device@comma.ai >
Co-authored-by: Maxime Desroches <desroches.maxime@gmail.com >
2024-12-18 11:58:59 -08:00
7352e612a2
dmonitoringmodeld: use cl transform without tinygrad ( #34266 )
...
* merge
* why
* self.buf_size
* 0.05 more than with tg due to copy
---------
Co-authored-by: Comma Device <device@comma.ai >
2024-12-16 16:29:06 -08:00
5018cf75ff
North America Model ( #34260 )
...
* 0e1c9c12-0472-4a0c-8963-611ad240ec62/400
* rm outputs
2024-12-16 14:17:31 -08:00
f6885dcbec
Revert Tinygrad ( #34243 )
...
* Revert "dmonitoringmodeld: use cl transform (#34235 )"
This reverts commit 684b0b9d4d31606a7d1544f58ff758#34171 )"
This reverts commit 7b5a4fbb03
2024-12-14 12:15:36 -08:00
684b0b9d4d
dmonitoringmodeld: use cl transform ( #34235 )
...
* needs cleanup
* only if tici
* bump tinygrad
* check width
* base modelframe
* .
* need to be args
* more cleanup
* no _frame in base
* tici only
* its DrivingModelFrame
* .6 is fair
---------
Co-authored-by: Comma Device <device@comma.ai >
2024-12-14 00:44:15 -08:00
8743bc4fe2
Null Pointer Model ( #34111 )
...
* e8cb7f27-e448-4c15-90c2-ac440cd5a042/400
* 0078ad07-4d46-4086-820f-23d61c90e07f/400
* 4bd74082-70af-47da-8156-e84ebf4d4812/400
* 2a074022-5c2c-4628-97f9-f54849a936a6/400
* 0660aa81-93c5-41b7-9cc2-dc8816a512cd/400
* Clip curvature to reasonable limits
* Better curvature and speed clips
* typo
* typo
* 31aa62c3-b373-4878-8f2e-5107305de187/400
* 384690ca-9b8a-41fe-9bcd-389b20fc6aa4/400
* ref commit
---------
Co-authored-by: Yassine <yassine.y10@gmail.com >
2024-12-13 19:14:21 -08:00
7b5a4fbb03
Tinygrad runner ( #34171 )
...
* squash
* bump tg
* bump tg
* debump tinygrad
* bump tinygrad
* bump tg
* Skip init iteration
* fixes
* cleanups
* skip first test sample
* typos
* linter unhappy
* update cpu usage
* OPENCL just zeros for now
* imports
* Try printing
* Runs again, but slower
* unused import
* Allow more buffer with tg and all on gpu
* bump tinygrad
* seems ok
* stricter timings for driving looser for dm
* try llvm
* check nvidia
* More timeout for now
* make test pass
* Revert "try llvm"
This reverts commit ef136e478320101fea262bae3579e558da991902.
* small fixes
* whitespace
* revert test timeout
* No model runners
* Always CPU always fast
* No onnx runtime GPU
* more cores
* cleanup
* Is this faster
* Is this faster
* at least runs
* FP32 is faster than 16
* fix deps
* whitespace
* comment
---------
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com >
2024-12-11 23:15:20 -08:00
57fc4f79d1
Postal Service Model ( #34183 )
...
0d68d465-9938-4327-a015-0cef58bc9f3a/400
2024-12-09 13:13:01 -08:00
7a4169379d
Revert "PlayStation® model ( #34133 )" ( #34170 )
...
This reverts commit 5160bee543
2024-12-06 23:56:53 -08:00
5160bee543
PlayStation® model ( #34133 )
...
* e2a90efd-8986-4c97-8f55-22725cdee8b9/400
* bea47b6f-c2f9-460f-9658-73f202756294/400
* 7e8efd49-f1a4-4355-912e-610633e0e7f9/390
* 7e8efd49-f1a4-4355-912e-610633e0e7f9/400
---------
Co-authored-by: Bruce Wayne <harald.the.engineer@gmail.com >
2024-12-02 23:44:21 -08:00
81252f549c
Alabama model ( #34108 )
...
e22d5e0c-1441-4953-b878-8f0f36e527c6/400
2024-11-25 14:34:36 -08:00
fee1f29ce9
Last Horizon Model ( #34090 )
...
* 516b3968-82ec-4d7c-89ff-57ded21b3966/400
* 074f0168-aa4a-456b-a82c-464a6fc4ecdf/400
* f3dede04-b52d-4ca1-83aa-9686bd9d49ae/400
2024-11-22 19:19:55 -08:00
612dbb32e1
Revert "Last Horizon Model ( #34024 )"
...
This reverts commit e123ac3d32
2024-11-18 09:32:54 -08:00
e123ac3d32
Last Horizon Model ( #34024 )
...
516b3968-82ec-4d7c-89ff-57ded21b3966/400
2024-11-18 09:31:13 -08:00
d9d57e5d6f
Revert ISP image processing + tinygrad bump ( #34020 )
...
* Revert "Replace ThneedModel with TinygradModel (#33532 )"
This reverts commit da952e9b64#33959 )"
This reverts commit f2a1cce42b
2024-11-13 19:27:11 -08:00
da952e9b64
Replace ThneedModel with TinygradModel ( #33532 )
...
* squash
* bump tg
* bump tg
* debump tinygrad
* bump tinygrad
* bump tg
* Skip init iteration
* fixes
* cleanups
* skip first test sample
* typos
* linter unhappy
* update cpu usage
* OPENCL just zeros for now
* imports
* Try printing
* Runs again, but slower
* unused import
* Allow more buffer with tg and all on gpu
* bump tinygrad
---------
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com >
Co-authored-by: Bruce Wayne <harald.the.engineer@gmail.com >
2024-11-11 13:32:21 -08:00
47bd0f0166
Dragon Rider Model ( #33958 )
...
* c77e258c-8e59-46aa-a2ef-09398823e801/400
* 04a1d006-4d46-499a-a27e-dfe9651398a9/400
2024-11-09 17:28:20 -08:00
34dde0bb36
MLSIM V4 ( #33809 )
...
bf0b9aac-ca49-446d-9274-81dcc7c28621/400
2024-10-17 13:14:09 -07:00
682857f0cd
MLSIM V3 ( #33745 )
...
* 09366265-2385-4c47-85a9-009aaabc283d/400
* 7a744f78-ac70-4070-b2b2-fd25b736667b/400
* ff6c6166-a9e0-40bc-8867-b0b35bcad8b8/380
* 241215ad-05e1-4153-8fc9-5108c6002123/400
2024-10-09 13:23:52 -07:00
2040f04c45
MLSIM V2 ( #33727 )
...
* bb2f7438-51f1-41ce-b337-238eaf2fd14d/100
* bb2f7438-51f1-41ce-b337-238eaf2fd14d/110
* bb2f7438-51f1-41ce-b337-238eaf2fd14d/330
* c3aa47aa-a00e-4b42-a40b-526039378a3a/400
* bd637aab-4274-41c1-95ac-25fb8bf88547/400
* Update ref
* 5705291a-5f7b-4849-91e8-4b0ea87f44d3/400
* 9f345169-a30d-4fec-bf06-2a457bf0071f/400
* update refs
---------
Co-authored-by: Yassine <yassine.y10@gmail.com >
2024-10-07 09:40:27 -07:00
2b486b15c6
MLSIM trained model V1 ( #33698 )
...
* 87c86ea8-9766-43e9-b72f-185496800301/400
* update ref
2024-10-02 14:47:09 -07:00
e442425c9d
MLSIM trained model V0 ( #33676 )
...
* squash f7343ba0-3f7d-4776-9819-2219b8d2d667/270
* fix broken ref
* Model replay ref commit
2024-10-01 02:58:20 -07:00
19bd96004e
Cleanup shift ( #33677 )
...
* Cleanup shift code
* Unsafe buffer copy
* fix bugs
2024-09-29 23:23:16 -07:00
3b08501db3
Game Boy Model V3 ( #33674 )
...
* f4afab38-2ee3-4a71-904a-f2e5d4ec119a/400
* Model replay
* fix onnx cast
* tol
2024-09-29 20:33:35 -07:00
390eee0717
Revert "onnx model needs cast"
...
This reverts commit a2b3b1540d
2024-09-29 20:02:32 -07:00
a2b3b1540d
onnx model needs cast
2024-09-29 19:48:31 -07:00
edf9522bc0
Model and YUV pipeline to uint8 ( #33671 )
...
* Squash
* 78cec5a0-577b-49ac-b443-f7cd327649bd/400
* bump tinygrad
2024-09-28 18:34:31 -07:00
4da090a4e1
Game Boy Model V2 ( #33669 )
...
* 78cec5a0-577b-49ac-b443-f7cd327649bd/400
* ref commit
2024-09-28 15:33:01 -07:00
04a266eaeb
Game Boy Model ( #33661 )
...
* 559069cd-40a6-4456-9052-08659f376ca3/370
* 028fb9bc-b33e-4c26-9cf7-e3c44a85276a/400
* Update ref
* Update tolerance
2024-09-27 22:48:32 -07:00
876f192112
exec DM model with gpu ( #33609 )
...
* half
old-commit-hash: 9f72eca003d4637ca7fe847ebaf925c694fc2e84
* optimed
old-commit-hash: 6e36e2a12e09275ec21d1590012a92b05ca52ff5
* thneed
old-commit-hash: 419a06c09c0c767d828bcd1e118bc575898c343a
* exec
old-commit-hash: 0059c27ec11b076a37f65d604ed135ea6541b1a6
* runner
old-commit-hash: 34232ada94450ce541eaef546197fa219810a891
* runs but
old-commit-hash: 3db37c00b6a64908293b4de8d8b56e80308cd8f2
* it is 01
old-commit-hash: a160d81eb1a7e77abbef959b44f602610f68f665
* np
old-commit-hash: c1caff6ba648cc2c0094c71b2ea074f01c3c2dc8
* module url
old-commit-hash: 6f4902c4d384263a53e2c1d14d93b5ff864b6a5f
* new
old-commit-hash: 779ae79b1bc3df6374fb6663ac8592e107a6e504
* ds fast
* is this work
* corcention
* real timing
* no reg
* interim gather
* 0e4a9c7b
* fa69be01, and halve
* list
* cleanup
* slighly faster
* setprotlt
* expected
* replay ref
* more powar
* reluctantly
* bump tg
* 8
* less
* less
* bump tg
* better than exp
* closer
* cc
* see diff
* commits
* was right
* to 32 cast
* remove dlc file
* support both
* dspExecutionTime -> gpuExecutionTime
* ignore
* time ref
* ref commit
* last
---------
Co-authored-by: Comma Device <device@comma.ai >
2024-09-26 16:40:44 -07:00
251e2e9400
Clip sigmoid overlfow ( #33635 )
...
* No more C sigmoid
* Clipping
* Need to cast to float
* Update ref
* Clip
* Model refg
2024-09-23 19:06:52 -07:00
e8bea2c78f
Tomb Raider Model ( #33629 )
...
* 69acff08-5383-4103-beea-822f0d228c76/160
* 53f39907-4763-4d19-ba26-e757527c2b61/200
* 21afb89f-1397-4652-b423-abc2da32417a/200
* 21afb89f-1397-4652-b423-abc2da32417a/400
* 53f39907-4763-4d19-ba26-e757527c2b61/400
* 3fb967fd-16a8-4569-ba57-359e54deeab3/395
* Try other policy again
* 3fb967fd-16a8-4569-ba57-359e54deeab3/400
* 0136cabf-539a-4a43-bc7f-06c3654a493c/4400
* 473c0686-1ac9-4c05-9b0b-d1f1afdb6cc3/400
* 83b7993d-51a9-4e3f-904e-3fcd5763c231/400
* 021566c7-cff3-431d-8da2-17a96c888c5f/400
* Fix bugs
* Update longitudinal_planner.py
* Update fill_model_msg.py
* 8be6b59d-4449-42fd-b8e0-93c48387070f/400
* f670a748-3591-4489-a0b3-215118ddad01/400
* 790a2950-c713-4eec-838b-4f55f4fe0ccb/400
* Update model ref
* Plans start at ego
* Update ref
2024-09-23 14:26:28 -07:00
ffb6e11f96
Revert "exec DM model with gpu" ( #33604 )
...
Revert "exec DM model with gpu (#33397 )"
This reverts commit f79aca8e1e
2024-09-19 20:55:11 -07:00
f79aca8e1e
exec DM model with gpu ( #33397 )
...
* half
old-commit-hash: 9f72eca003d4637ca7fe847ebaf925c694fc2e84
* optimed
old-commit-hash: 6e36e2a12e09275ec21d1590012a92b05ca52ff5
* thneed
old-commit-hash: 419a06c09c0c767d828bcd1e118bc575898c343a
* exec
old-commit-hash: 0059c27ec11b076a37f65d604ed135ea6541b1a6
* runner
old-commit-hash: 34232ada94450ce541eaef546197fa219810a891
* runs but
old-commit-hash: 3db37c00b6a64908293b4de8d8b56e80308cd8f2
* it is 01
old-commit-hash: a160d81eb1a7e77abbef959b44f602610f68f665
* np
old-commit-hash: c1caff6ba648cc2c0094c71b2ea074f01c3c2dc8
* module url
old-commit-hash: 6f4902c4d384263a53e2c1d14d93b5ff864b6a5f
* new
old-commit-hash: 779ae79b1bc3df6374fb6663ac8592e107a6e504
* ds fast
* is this work
* corcention
* real timing
* no reg
* interim gather
* 0e4a9c7b
* fa69be01, and halve
* list
* cleanup
* slighly faster
* setprotlt
* expected
* replay ref
* more powar
* reluctantly
* bump tg
* 8
* less
* less
* bump tg
* better than exp
* closer
* cc
* see diff
* commits
* was right
* to 32 cast
* remove dlc file
* support both
---------
Co-authored-by: Comma Device <device@comma.ai >
2024-09-19 17:42:44 -07:00
29dda3b232
Fix FutureWarning "Cython directive 'language_level' not set" ( #33046 )
...
fix FutureWarning
old-commit-hash: fb3336614484553456bee6c2116b729177ecbc46
2024-07-23 09:27:10 -07:00
e0c89a36da
Notre Dame model ( #32884 )
...
* New model: 6f23a03f-486b-4d3e-a314-19d149644c7c/700
* Bump refs
old-commit-hash: 01c2174d5968266b87f1d1fecefce5affaeaa624
2024-07-01 13:59:44 -07:00
f870a968e9
Split cereal into cereal/msgq ( #32631 )
...
* squash
* fix doc
* compile device
* compile device
* Update ref
* add msgq to precommit exclusions
* No service ports
* fix compile
* address comments
* More comments
* Delete logger
* Update opendbc
* Linting
* bump msgq
old-commit-hash: e71ec4e8d7e39a56235f590227e7cb361cd8b79d
2024-06-06 14:31:56 -07:00
6e4c3ddb40
modeld: cleanup commonmodel ( #32618 )
...
cleanup
old-commit-hash: 2482ed085ebfd2c09394ce59900348334772d58f
2024-06-04 11:20:17 -07:00
3ad7205042
Revert "wip /500"
...
This reverts commit 3baaa27c2defbdd4ec29805c2641b9e8a82a35ce.
old-commit-hash: 8bd4540636cf36eb59efcc0ee3a0f0ad81fbb680
2024-05-24 19:45:00 -07:00
c40976bb5f
wip /500
...
old-commit-hash: 8183715beb961658755b2f19dbba6b07582830cd
2024-05-24 19:44:14 -07:00
5218ec9e60
fix(modeld): Fix for unpredictable behavior in commonmodel_pyx.pyx ( #32482 )
...
Avoid undefined behavior
Co-authored-by: 19igari <koki.igari@turing-motors.com >
old-commit-hash: 25cc8a96ef22df5c8d6951c159045ae4e6d94807
2024-05-21 18:41:04 -07:00
Shane Smiskol