sirhcm/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests 2 Actions 8 Activity
12,577 Commits 336 Branches 15 Tags
cafa3b74d4c8bd4e75fca5f5eee856ab2b6b76ee
Commit Graph
12577 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
ttomsa cafa3b74d4 rm bad rewrite 2026-03-02 21:32:52 +00:00
ttomsaandGitHub 393e591f49 Merge branch 'master' into new_x86_backend 2026-03-02 21:14:07 +00:00
ttomsa 82954c7ca4 support float16 vector load/store 2026-03-02 21:13:07 +00:00
chenyuandGitHub 14d1c5fdfd assign fusion tests on detach and contiguous_backward (#15092) 2026-03-02 15:21:51 -05:00
nimlgenandGitHub dfa180413d tbgpu: sign nv (#15087) 2026-03-02 22:58:30 +03:00
chenyuandGitHub 71f228f80f test exact kernel count in torch_backend/test_kernel_fusion (#15091) 2026-03-02 14:26:32 -05:00
chenyuandGitHub f80b1033c5 simpler Tensor.all (#15089) 
same generated kernel
 2026-03-02 11:08:55 -05:00
chenyuandGitHub 4008f7d4e8 move Tensor.one_hot +1 to python (#15088) 2026-03-02 10:56:41 -05:00
nimlgenandGitHub dafbe9733a am: cleanup (#15086) 2026-03-02 17:06:21 +03:00
qazalandGitHub f7aeff6061 viz: cli.py cleanups, do not require PYTHONPATH (#15085) 
* cleanup the print

* sys.exit

* equal check

* cleanup unpacker

* cli doesn't need PYTHONPATH

* no semicolons

* %s/PYTHONPATH=. //g
 2026-03-02 19:24:38 +09:00
George HotzandGitHub 5ff278446c add contiguous_view_offset (#15084) 
* add contiguous_view_offset

* no int
 2026-03-02 18:05:04 +08:00
sirhcmandGitHub 977c270774 IMAGE=1 kernel count failing tests (#15083) 2026-03-02 04:35:26 -05:00
George HotzandGitHub 3539693555 Support triu variable on diagonal + SDPA symbolic (#15081) 
* triu variable

* fails

* dumbbb

* no commutative in reshape

* real fix

* revert that

* sdpa symbolic tests
 2026-03-02 12:19:48 +08:00
wozeparrotandGitHub a4f6365929 llama3: fstep takes grads (#15069) 2026-03-01 20:05:07 -08:00
NickGitHubGeorge Hotz
 		8e8e9f6ff6 assert removal for _tri() + tests (#15073) 
* assert removal for _tri() and tests

* removed import

* tests triu/tril like in prefill

---------

Co-authored-by: George Hotz <[email protected]>
 2026-03-02 10:34:28 +08:00
nimlgenandGitHub ccbbca05ef beam: add dev_timeout for am (#15063) 
* beam: add dev_timeout for am

* all covered

* fk

* x

* fuzz

* reset

* f
 2026-03-01 16:57:29 +03:00
chenyuandGitHub 8cb4368967 delete unused END NOOP rule [pr] (#15077) 2026-03-01 00:09:05 -05:00
chenyuandGitHub efce99adc9 skip isComposing key press in llm.py (#15076) 
for the CJK input user
 2026-02-28 20:31:53 -05:00
chenyuandGitHub 103ea16ec0 add contiguous back to svd (#15074) 
can cause infinite loop
 2026-02-28 16:49:26 -05:00
chenyuandGitHub fe0fa8333b Revert "improve Tensor.sort indices (#15070)" (#15072) 
This reverts commit e3003631f2.
 2026-02-28 14:40:30 -05:00
chenyuandGitHub e3003631f2 improve Tensor.sort indices (#15070) 
* improve Tensor.sort indices

instead of N^2 match at the end, have an arange to start and go through the same N(logN)^2 path

* contiguous
 2026-02-28 14:16:16 -05:00
wozeparrotandGitHub cfc5cf65ad llama3: vocab padding fix + jit copies on fakedata (#15067) 2026-02-28 08:44:55 -08:00
chenyuandGitHub 76170d035a relax atol for test_xlm_roberta_large (#15066) 2026-02-28 11:22:35 -05:00
qazalandGitHub cfb8e6922d viz: arrow keys move through time (#15064) 
* work

* automatic zoom, keeping scale

* the whole shape should be out of view
 2026-02-28 23:52:36 +09:00
nimlgenandGitHub 9b3450c9da test gpu crash on cdna (#15062) 2026-02-28 13:17:59 +03:00
nimlgenandGitHub 6bbf813dd3 ci: switch to tinygrad/amdcomgr_dylib (#15061) 2026-02-28 13:09:39 +03:00
nimlgenandGitHub 77846300b2 am: reset vm fault (#15060) 2026-02-28 12:58:56 +03:00
George HotzandGitHub dc54441e1f add better printing to tinygrad.apps.llm (#15059) 
* add better printing to tinygrad.apps.llm

* add gc.collect

* comment
 2026-02-28 16:38:50 +08:00
George HotzandGitHub bb84e389cf functions for llama trainer (#15045) 
* functions for llama trainer

* function there

* axis match

* fix multi

* lil cleaner

* there's a bug with HK_FLASH_ATTENTION

* training functions

* for commit
 2026-02-28 12:15:18 +08:00
chenyuandGitHub 9b4ba3f838 remove ReduceContext.range_to_ends [pr] (#15055) 
* remove ReduceContext.range_to_ends [pr]

make merge_reduce_ends pure. this state is causing issue when introducing more reduce merging rewrites

* tag
 2026-02-27 22:15:44 -05:00
chenyuandGitHub 151608aa90 update test_multiple_to_single_device (#15056) 
follow up to #14482, add SCACHE=0 to the test
 2026-02-27 21:44:33 -05:00
ttomsa eb4ad1ebf0 move max/min and add test 2026-02-27 22:52:50 +00:00
ttomsaandGitHub ce2c690721 Merge branch 'master' into new_x86_backend 2026-02-27 22:40:28 +00:00
ttomsa a982a8709e canonical max 2026-02-27 22:38:16 +00:00
chenyuandGitHub 5fd06f4f02 differentiable setitem (#15054) 
* differentiable setitem

go through the where path for bw

* no return
 2026-02-27 17:25:15 -05:00
ttomsa 94c317a437 print correct reg names 2026-02-27 22:23:11 +00:00
chenyuandGitHub db6b3e1edc fix mixed setitem with both basic and tensor indexing (#15050) 2026-02-27 15:35:48 -05:00
chenyuandGitHub c9f6d8751b don't remove_bufferize for Invalid (#15053) 
* don't remove_bufferize for Invalid

* replaced
 2026-02-27 15:16:09 -05:00
qazalandGitHub b8a55d5f68 sqtt: new packet types, add discovery script (#14960) 2026-02-28 04:27:27 +09:00
nimlgenandGitHub 4e12fc3fe6 am: mi3xx recovery (#15051) 2026-02-27 22:10:47 +03:00
chenyuandGitHub 81a35cef38 rearrange Tensor.getitem code (#15049) 
no-op change to prepare setitem fix
 2026-02-27 12:57:16 -05:00
chenyuandGitHub 1406d49eef failed test cases for advanced setitem (#15048) 2026-02-27 10:50:18 -05:00
qazalandGitHub ef1017f7ed viz: skip drawing offscreen tracks in profiler (#15047) 2026-02-27 22:19:08 +09:00
qazalandGitHub ad99b77f6d assembly/amd: add gfx12_asm_vflat llvm tests, disasm fixes (#15046) 
* add gfx12_asm_vflat.s

* work
 2026-02-27 20:20:31 +09:00
George HotzandGitHub 010d2790ce fix multi minimal (#15044) 2026-02-27 14:31:58 +08:00
geohot 3e1e12528c hotfix: disable tinyfs load test 2026-02-27 12:04:41 +08:00
George HotzandGitHub d23b79530e remove disk from GGUF GEMV test (#15041) 
* remove disk from GGUF GEMV test

* keep copy
 2026-02-27 12:03:00 +08:00
chenyuandGitHub d345f7f5dc remove _pending_assigns (#15040) 2026-02-26 22:38:10 -05:00
George HotzandGitHub 37e31e7da4 gguf gemv test (#15039) 
* add gemv tests

* gguf big

* skip

* make realize optional
 2026-02-27 10:54:43 +08:00
NickandGitHub af94bfc401 fix retinanet shared memory race condition in parallel tests (#15030) 
Append PID to shared memory names in batch_load_retinanet to prevent
FileExistsError when pytest-xdist runs multiple test workers that each
call _setup_shared_mem with the same hardcoded name.
 2026-02-27 08:36:24 +08:00