nimlgen/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests Activity
12,186 Commits 334 Branches 15 Tags
emu_cdna
Commit Graph
12186 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
George HotzandGitHub 6e3a120c31 Fix cache invalidation check in _compile_smem 2026-02-13 15:48:23 +08:00
geohot 4c24f61f3f round 2026-02-13 07:14:46 +00:00
geohot e47c8c7e0b delete that 2026-02-13 06:57:57 +00:00
George HotzandGitHub b808724318 Merge branch 'master' into emu_cdna 2026-02-13 14:54:50 +08:00
geohot 0ce525abfe REMU_PATH 2026-02-13 06:54:25 +00:00
geohot 10dce913bb no early 2026-02-13 06:48:01 +00:00
sirhcmandGitHub 08a555c875 skip test_expand_buffer_before_cast on WEBGPU metal (#14724) 2026-02-13 00:01:05 -05:00
sirhcmandGitHub 7993f3a277 autogen: use snapshot.debian.org for linux src (#14718) 2026-02-12 23:36:38 -05:00
wozeparrotandGitHub 0613c0ac0c hipkittens fa forward (#14692) 2026-02-12 20:16:43 -08:00
chenyuandGitHub 50cb40be88 clean up test/null/test_indexing.py (#14720) 2026-02-12 22:36:53 -05:00
geohot d89cb880b2 no predecode 2026-02-13 03:26:12 +00:00
qazalandGitHub 5b624b5e93 viz: better error message for out of range timestamps (#14722) 
* test_timestamp_out_of_range

* rel_ts helper

* linter
 2026-02-13 12:13:40 +09:00
geohot f2894675c0 fixes 2026-02-13 02:58:37 +00:00
George HotzandGitHub 4088d686b2 remove llvm requirement from amd (#14717) 
* remove llvm requirement from amd

* tests pass

* test

* sink kernarg_size

* move stuff

* amd_asm_matmul to new style

* default type

* fix tests, simpler

* cu mode is faster and simpler

* darken
 2026-02-13 10:50:12 +08:00
George HotzandGitHub 5e97a25b66 Merge branch 'master' into emu_cdna 2026-02-13 10:42:04 +08:00
geohot f77da7ed89 renderer/amd: add cdna emulator 2026-02-13 02:38:08 +00:00
chenyuandGitHub 9e33a08adb use more pad_to and shrink_to in tensor.py (#14719) 
good wins
 2026-02-12 20:10:57 -05:00
George HotzandGitHub d3adb8428e Revert "hotfix: skip test/amd in macpytest" (#14704) 
* Revert "hotfix: skip test/amd in macpytest"

This reverts commit b7dade2adf.

* no llvm subprocess

* simpler

* sys.exec

* cleanup

* process safe

* diag

* arm ftz support

* 5 sec

* this one
 2026-02-13 08:00:24 +08:00
sirhcmandGitHub d4bc5ab609 autogen: download linux sources (#14714) 2026-02-12 18:50:50 -05:00
sirhcmandGitHub 084d0d0103 cleanup macos webgpu tests (#14715) 2026-02-12 17:56:34 -05:00
sirhcmandGitHub c30bb0f006 fix WEBGPU isnan check (#14711) 2026-02-12 17:01:18 -05:00
chenyuandGitHub 9b3b597423 minor getitem cleanups (#14713) 2026-02-12 16:54:54 -05:00
chenyuandGitHub 787998fac3 fix getitem tensor indexing detection (#14712) 
issue with sint
 2026-02-12 16:04:37 -05:00
chenyuandGitHub 86352988d8 update test_uops_stats for setitem (#14710) 
realize both full tensor and the slice should not add to global_mem
 2026-02-12 12:26:13 -05:00
chenyuandGitHub 56caf6a3a2 fix Estimate.from_uops for sliced access (#14695) 
"assume all DEFINE_GLOBAL memory is accessed" is wrong for partial load. get accessed accumulated from INDEX, then cap at full size. now mem_est never exceeds lds_est
 2026-02-12 11:18:07 -05:00
chenyuandGitHub 8551fa50d3 support bitcast in sym_infer (#14708) 
fixed `DEBUG=2 DEV=WEBGPU python -m pytest test/backend/test_tensor_variable.py::TestTensorVariable::test_symbolic_pad`
 2026-02-12 10:21:05 -05:00
chenyuandGitHub 212789e31e fix long_decomp with None tag (#14707) 
fixed `DEBUG=2 WEBGPU=1 python -m pytest test/null/test_tensor.py::TestIdxUpcast::test_int64_unsupported_overflow_sym`
 2026-02-12 09:31:52 -05:00
chenyuandGitHub 557134e1c7 model/test fix that failed with WEBGPU=1 DEBUG=2 (#14706) 2026-02-12 09:08:16 -05:00
nimlgenandGitHub 10c94d2c2d amd: print more info about device hang (#14705) 2026-02-12 15:34:08 +03:00
nimlgenandGitHub b376bd7a21 jit: fix raw in same kernel (#14699) 
* jit: fix raw in same kernel

* fix

* ugh

* x

* simpler
 2026-02-12 15:33:32 +03:00
George HotzandGitHub 19e68a1833 skip AMD on not AMD (#14703) 2026-02-12 18:56:54 +08:00
geohot b7dade2adf hotfix: skip test/amd in macpytest 2026-02-12 18:16:04 +08:00
George HotzandGitHub 4680247e35 renderer/amd: move in tree (#14702) 
* renderer/amd: move in tree

* fix paths in tests

* 24000 lines

* no delete for amd files
 2026-02-12 18:09:16 +08:00
George HotzandGitHub d5fc3ea1ba assembly/amd: mypy+ruff passes (#14701) 
* assembly/amd: mypy+ruff passes

* touchups
 2026-02-12 16:59:42 +08:00
George HotzandGitHub 095a064ba8 test.yml explicitly says backend (#14700) 
* test.yml explicitly says backend

* 1e-5
 2026-02-12 16:03:44 +08:00
nimlgenandGitHub 14a1991da6 viz: sort tracks in timeline (#14591) 
* viz: sort devices in timeline

* fix

* rev

* upd

* skip
 2026-02-12 10:51:41 +03:00
George HotzandGitHub 025049c521 clean up sqtt / update src formatting in viz (#14696) 
* update src formatting in viz

* rename to RDNA3/RDNA4 in sqtt

* wrap

* move sqttmap

* update readme

* why did that change?

* cdna

* that's just for test
 2026-02-12 14:27:14 +08:00
sirhcmandGitHub b1a3876492 IMAGE=1 supports FLOAT16=1 (#14693) 
requires 2d indexing to be actually fast
 2026-02-12 00:30:55 -05:00
George HotzandGitHub befc1e800c assembly/amd: disasm is test only (#14694) 
* assembly/amd: disasm is test only

* viz uses str
 2026-02-12 12:33:46 +08:00
George HotzandGitHub c331798201 move tests to test/backend (#14691) 
* move tests to test/backend

* fix imports

* fix CI

* revert that one

* Fix formatting in README for test command
 2026-02-12 11:09:44 +08:00
wozeparrotandGitHub 4b5d3bda1f llama3: data seed (#14681) 2026-02-11 19:04:40 -08:00
chenyuandGitHub 0c63f63ee4 recursive resolve assign dependency (#14688) 
remove the .realize in llm.py
 2026-02-11 17:41:05 -05:00
nimlgenandGitHub 869083e373 nv: pciiface pma (#14686) 
* x

* w

* z

* clean

* o

* r

* x

* c

* r

* list

* deanon

* b
 2026-02-11 23:29:07 +03:00
chenyuandGitHub cbbc2fdea5 update test_assign_slice_then_read (#14687) 
passes locally now
 2026-02-11 15:02:44 -05:00
chenyuandGitHub 7465b22ba0 handle setitem target in rangeify (#14685) 2026-02-11 11:38:59 -05:00
chenyuandGitHub 0d215b962e few setitem test cases diff from numpy (#14684) 
have claude fuzzed frontend and found some real bugs
 2026-02-11 08:41:03 -05:00
nimlgenandGitHub df8b21eeb5 add real self assign test (#14683) 
* self assign fix

* no
 2026-02-11 12:41:53 +03:00
wozeparrotGitHubGeorge Hotz
 		a60220bed9 llama3: move dl to numpy & jit more (#14677) 
Co-authored-by: George Hotz <[email protected]>
 2026-02-10 18:16:40 -08:00
George HotzandGitHub 4565958792 some lil speedups (#14679) 2026-02-11 10:01:58 +08:00
George HotzandGitHub 2d4ad9e739 add a waitlist for graph rewrite (#14678) 
* add a waitlist for graph rewrite

* cleaner

* one context on spec check
 2026-02-11 09:30:13 +08:00