Commit Graph

Select branches

Hide Pull Requests

abstractions_4

add_local_buffer

after_qol

algebraic_upat

all_bv_no_idx

all_sink

amd_isel

amd_refac

amd_smu_reset_patch

amd_sqtt

amd_uop

amd_uop_cleanups

assign_copy

assign_try_3

before2

better_spec

better_syn

bitcast_spec

broadcast_shape_2

bt_ei

buf_heur

bump_nv_2404

cache_reshape

call_inline

call_is_kernels

callify

cast_vec_as_cast

cat_mop

changes_from_rangify

check_clsetarg

check_dims

cifar_30

cifar_30_clean

clean_load

clean_spec

clone_tg

codegen_try_2

contig_on_after

continue_mat

deepsek

default_late_allreduce

delete_kernel_py

delete_ones

delete_slow_rangeify

delta_attention

delta_attention_scan

demote_op

disable_rules

dsp_search

dsp_search_merged

dtype_shape

earlier_gater

emu_cdna

emulate_ctx

end_all_ranges

endrange

er_prioity

execution_unit

failing_assign

fancy_usb

fast_llm

fix_fa_fwd_clang_22

fix_fuse

fix_llvm_cast

fix_range_merging_sd

fix_rangeify_tests

fix_rc

fix_sched_copy

fix_slice_store

fix_src_spec

fixup_fix_kernel

full_spec

fun_w_egraphs

gate-on-load-store

gate_rewrite

gemma4_gpt

gen_pdf_fast

gh-pages

gl_dims

gldims

glm_flash

grad_outerworld

grok_x86_novec

group_div_rules

hcq2_vram_copies

heur_4096

heur_group

hk_gemm

http_threading

hwtest_fixes

id_store

if_range_cleanups

ignore_oob

image_idx_xy

image_in_mc

image_no_vec

image_refactors_stack

index_to_slice

invalid_try_3

jinja_template

kernel4

kernel_is_call

kernelless

kimi_slop

kitten_matmul

late_Locals

late_add_load

late_allreduce

late_codegen

late_decomp_is_late

late_lower_idx

late_view

late_weakint

lds_double_buffering

less_wmma_arg

lil_dg_change

lil_rangeify_td

llama_trainer

llm_262k_minimal

llm_flash_attn

llm_qwen

llm_serve_fixes

load_view_late

local_cache

locals_have_device

loop_end_op

loop_is_rng

lowerer_hacks

mac_pytest

manual_kernel_3

master

mega_lowerer

min_new_lin

min_outer_range

minor_views

mixins7

mlperf_training_v4.1

mlperf_training_v5.0

mlperf_training_v6.0

modern_scan

more_apps

more_early_comps

more_folding_rules

more_kernelcount

more_pcode

more_rangeify_pm_tests

more_ren_clean

more_uop_gc_test

more_uop_mm

more_vmap

move_devec

move_dtype_decomps

move_expander

move_gates_to_load_store

move_mop_cleanup

move_schedule

move_simp_views

moveleftright

mt_typing

multi_range

multioutput

new_ck

new_devec

new_invalid_and_image

new_linearizer

new_shape

new_test

no_assign_2

no_buf_0

no_decimals

no_late_simplify_marg

no_merge_ends

no_merge_views

no_mstack_in_allreduce

no_one_ranges

no_sip_usbgpu

no_tsink_base

no_tuplize

no_user_ck_contig

no_vec_x86_4

no_weakint_variable

noop_index

novecimg

num_batches_tracked_shape

olmo3_support

one_compiler

one_hcopt

only_assign_buffers

only_loop_backends

only_reg_emu

only_reg_emu2

outer_range

outerworld_work

pad_invalid_work

pad_mixin

param_call_is_function

parse_sqtt_more

pci_iommu

port_nir

postrange_hcopts

precompile_backward

prefill_qwen_fast

print_special_ops

ps_clean

pyremu_try

python_prg

python_speed

q4k_support

qcom-openpilot-13ms

qcom_830

qcom_mmapeak

qcom_speed_codex

qol_string

qwen36_27b_amd_900

qwen36_27b_amd_minimal

qwen36_amd_bugfixes

qwen_mergable

r_cleanups

r_new_opt

ranged_call

rangeify_2

rangeify_const_folding

rdna3_vibes

rdna4_asm

rdna4_gemm

real_pyrender

recurse_sub

reg_coalese

relu_pattern

remove_assign

remove_cast_hack

remove_ck_contig

remove_define_var

remove_forced_re

remove_on_stack

remove_programspec

remove_pylint

remove_slow_tests

remove_vec_2

remove_vec_3

renderers_use_shapes_2

replace_if_with_range

reprocess_node_experiments

reshape_trait

resnet-ci

revert-11547-fix_mismatch_red

revert-11715-revert-11711-amd_llvm_tc_cast

revert-11809-no_ki_in_gpudims

revert-11811-better_div_nesting

revert-11876-memplan_vbig

revert-12104-simplify_valid_in_symbolic

revert-12308-bufferize_early

revert-12731-jitlink_init_check

revert-12813-after_cleanups

revert-13046-better_cleanup_arange_buffers

revert-13311-prof_link_sqtt

revert-13583-rocr_desc_2

revert-14734-tload

revert-17141-full_rewrite_to_sink

revert-17408-_broadcasted-weak

revert-9438-simple_matmul_np_rand

revert_wrong_ck_fix

rewrite_rangeify2

rtoposort

scan_assign

scan_op_8

sched_cache

sched_lin

sd_load_simple

self_type

set_testpath

shrink_in_render

simp_spec

simple_gidxs

simple_pool

simple_priority

simple_rangeify

simpler-sd-compile

simpler_end

simpler_fusion

simpler_image

simpler_postrange

simpler_reduce

slice_like_shrink

spec_3

spec_cleanup

spec_ren

speed_one_linear

split_buf_idx

split_decomp_pass

split_sub

stack_0

store_is_void

string_ranges

support_opts_in_contig

swizzle_in_kernel

sym_llm

sym_work

symbolic-chunk-split

szdiff_bot_test

tc_is_heur

tensor_graph_single_sink

test_amd_crash

test_fa

test_from_postopt

test_hgemm

test_unit

tiny_scan

tmr

tool_call_support

topoprop

ttomsa-new_linearizer

tuplegtuple

two_stage_remove

typed_checks

typing_work

unused_permute_arg

uop_prg

upd_test4

update_benchmark

update_benchmark_search

update_mlperf

user_failure

vecless_x86_glm

verify_sink_dims_clean

vf_ish

view_after_const

view_in_codegen

viz_cbroadcast

warp_fun

wgpu-f16-packed

working_postopt

x86_moves

x86_numel

v0.10.0

v0.10.1

v0.10.2

v0.10.3

v0.11.0

v0.12.0

v0.13.0

v0.4.0

v0.5.0

v0.6.0

v0.7.0

v0.8.0

v0.9.0

v0.9.1

v0.9.2

Mono Color

• bacabf0866 webgpu: fix enums (#16402) sirhcmandGitHub 2026-05-27 10:09:50 -07:00
• 6da785562b test_custom_kernel_precompile_multidevice (#16401) chenyuandGitHub 2026-05-27 11:19:16 -04:00
• 3e80f375ee skip test_setitem_fancy_on_unrealized_view (#16400) chenyuandGitHub 2026-05-27 09:50:26 -04:00
• 945ed4f689 revert const unique changes (#16395) chenyuandGitHub 2026-05-27 00:06:41 -04:00
• aacc8addf4 ci: use ubuntu 24.04 (#16393) sirhcmandGitHub 2026-05-26 20:22:01 -07:00
• fa14cde05c test update for arange and eye (#16394) chenyuandGitHub 2026-05-26 22:48:34 -04:00
• 2c8867c3e9 all cpu tests pass local index_to_slice geohot 2026-05-26 19:28:46 -07:00
• c88941a957 bugfix geohot 2026-05-26 19:19:44 -07:00
• 760acdf554 really fix llvm geohot 2026-05-26 19:16:48 -07:00
• f54a1d70d6 unneeded geohot 2026-05-26 19:05:04 -07:00
• 3a7a6da7d5 llama: fakedata uses real vocab size (#16389) wozeparrotandGitHub 2026-05-26 21:58:55 -04:00
• 5d3713a6be fix llvm geohot 2026-05-26 18:47:34 -07:00
• d0f956341c replace INDEX with SLICE geohot 2026-05-26 18:37:03 -07:00
• 1d55b5618c junk all_bv_no_idx geohot 2026-05-27 01:18:39 +00:00
• 4faa2b5bf3 can ai finish this geohot 2026-05-27 01:12:59 +00:00
• ee8ea27637 py geohot 2026-05-26 13:55:34 -07:00
• ab71e51ae1 cast also geohot 2026-05-26 13:36:31 -07:00
• 0cb3ce4811 spec buffer view instead of index geohot 2026-05-26 09:56:08 -07:00
• ff3b0c658d universal geohot 2026-05-26 08:55:33 -07:00
• 38bd43981b all BUFFER_VIEW, no INDEX geohot 2026-05-25 19:17:51 -07:00
• 156a4438d9 rename BUFFER_VIEW to SLICE (#16391) George HotzandGitHub 2026-05-26 18:15:00 -07:00
• 3adf7f5d95 disable flaky cl test (#16388) sirhcmandGitHub 2026-05-26 16:56:57 -07:00
• d23659d38b cleanup some old test skips (#16384) sirhcmandGitHub 2026-05-26 16:07:22 -07:00
• fd963038a0 remove allow_any_len from store (#16385) George HotzandGitHub 2026-05-26 15:26:53 -07:00
• 0b88827482 remove CONST(UNIQUE) (#16383) chenyuandGitHub 2026-05-26 14:45:22 -04:00
• d861c50dce remove unique_const (#16382) chenyuandGitHub 2026-05-26 13:53:31 -04:00
• bac82d4949 fix emu bug in gfx950 (#16381) George HotzandGitHub 2026-05-26 10:32:03 -07:00
• 9b00defc8c Revert "remove unique_const (#16372)" (#16380) chenyuandGitHub 2026-05-26 12:30:07 -04:00
• 09019d6761 remove unique_const (#16372) chenyuandGitHub 2026-05-26 12:18:03 -04:00
• 7f1b02854e bufferview offset is units of input dtype (#16378) George HotzandGitHub 2026-05-26 08:49:31 -07:00
• 846a809af7 viz: add +- toggle for hidden UOps (#16368) qazalandGitHub 2026-05-26 16:31:54 +03:00
• 032905dec9 hcq2: simpler (#16361) nimlgenandGitHub 2026-05-26 14:28:48 +03:00
• 322693dcd3 hotfix: bump Mac pytest timeout to 4 minutes (try 2) geohot 2026-05-25 18:23:21 -07:00
• 41ee7dab1c script to generate testsig for DSP (#16371) George HotzandGitHub 2026-05-25 17:54:58 -07:00
• 76fc39ccc0 gather to single device (#16354) wozeparrotandGitHub 2026-05-25 20:27:08 -04:00
• 942cb42b97 Revert "hotfix: bump Mac pytest timeout to 4 minutes" geohot 2026-05-25 17:25:11 -07:00
• 8ddd1328df remove getenv(CI) (#16365) sirhcmandGitHub 2026-05-25 17:23:33 -07:00
• 695a0069ed hotfix: bump Mac pytest timeout to 4 minutes geohot 2026-05-25 17:20:19 -07:00
• 689ab6a49f move buffer view offset to src (#16364) George HotzandGitHub 2026-05-25 17:07:55 -07:00
• d8f86be613 webgpu: shader-f16 support in arch (#16370) sirhcmandGitHub 2026-05-25 16:20:59 -07:00
• 4bcc53eb26 viz: stable node position for +- toggle (#16367) qazalandGitHub 2026-05-26 00:30:47 +03:00
• 3506eb08ec viz: sidebar toggles always recenter (#16366) qazalandGitHub 2026-05-26 00:14:32 +03:00
• cdeb861828 invalids is empty [pr] (#16353) chenyuandGitHub 2026-05-25 16:11:38 -04:00
• b73d2d17b9 viz/cli: add --interval (#16363) qazalandGitHub 2026-05-25 21:35:06 +03:00
• 2ab90f31b1 use windows-specific alias nvcuda when loading cuda on windows (#16260) C TandGitHub 2026-05-25 18:50:50 +03:00
• 68d2102fd2 llama: offload master weights (#16355) wozeparrotandGitHub 2026-05-25 11:48:13 -04:00
• eecd4706ff fix mailbox comment, add types (#16360) qazalandGitHub 2026-05-25 16:24:00 +03:00
• 64095cf2e2 use get_buf in exec_kernel (#16356) nimlgenandGitHub 2026-05-25 15:13:40 +03:00
• 5d5e02871f remove Tensor.from_uop (#16344) chenyuandGitHub 2026-05-24 18:53:09 -04:00
• a891727c9f hcq2: multi (#16347) nimlgenandGitHub 2026-05-24 19:28:33 +03:00
• 926d125a63 update test_stack (#16345) chenyuandGitHub 2026-05-23 10:42:35 -04:00
• 149a87dac2 deviceless const cleanups (#16341) chenyuandGitHub 2026-05-22 20:11:01 -04:00
• 35461d4d8f ci: cleanup some deps [pr] (#16340) sirhcmandGitHub 2026-05-22 16:16:08 -07:00
• 451f38155c start cleanup of the slowest tests (#16339) sirhcmandGitHub 2026-05-22 15:39:36 -07:00
• 26b3b3f6a2 hcq2: move submit lowering to schedule (#16330) nimlgenandGitHub 2026-05-22 23:15:19 +03:00
• 2d48fe8b7b feat: bump version to 0.13.0 (#16337) v0.13.0 wozeparrotandGitHub 2026-05-22 16:12:45 -04:00
• acc519720b add missing init files, add chat.html to package-data (#16334) chenyuandGitHub 2026-05-22 13:53:34 -04:00
• eeadf26dad Fix no module named error (#16305) 3 people 2026-05-23 01:51:29 +09:00
• 90dbb45563 nv: fix boot mem (#16332) nimlgenandGitHub 2026-05-22 19:28:38 +03:00
• 5d77a94923 am: mec_pipe0_reset on gfx12 only (#16331) nimlgenandGitHub 2026-05-22 19:02:18 +03:00
• bbfe4f80ec quantize_fp8 kernels in uops (#16288) qazalandGitHub 2026-05-22 14:54:06 +03:00
• 3115952266 more unique const removal prerequisite (#16328) chenyuandGitHub 2026-05-21 23:51:40 -04:00
• c2d06570a5 remove getenv(CI) from core tinygrad (#16326) sirhcmandGitHub 2026-05-21 19:20:33 -07:00
• 9744d512d9 use more non-buffered const (#16327) chenyuandGitHub 2026-05-21 21:37:52 -04:00
• 150a82de1f start cleaning up dtype tests (#16324) sirhcmandGitHub 2026-05-21 18:11:49 -07:00
• 31424cda71 Tensor.requires_grad -> is_param (#16325) chenyuandGitHub 2026-05-21 19:39:57 -04:00
• 518e60534e only load tinymesa_cpu when LVP is explicitly requested (#16320) sirhcmandGitHub 2026-05-21 16:03:13 -07:00
• 720a27bed8 remove many requires_grad= args (#16321) chenyuandGitHub 2026-05-21 18:37:11 -04:00
• 0c41317a59 llama: update 405b scripts (#16309) wozeparrotandGitHub 2026-05-21 17:03:34 -04:00
• fb718a5e9d llama: realize amax (#16308) wozeparrotandGitHub 2026-05-21 17:00:48 -04:00
• 73ea36f4ac full(buffer=True) (#16311) chenyuandGitHub 2026-05-21 16:34:44 -04:00
• 6815f28849 dtype.vec shapes (#16287) George HotzandGitHub 2026-05-21 11:56:49 -07:00
• afc5bfa183 llama: remove fused grad accum (#16301) wozeparrotandGitHub 2026-05-21 12:38:40 -04:00
• a321700baa hcq2: multi prereqs (#16304) nimlgenandGitHub 2026-05-21 17:00:52 +03:00
• e33e058d34 set SPLIT_W13=0 for 8b DP by default (#16302) qazalandGitHub 2026-05-21 16:09:10 +03:00
• dd279ee25e print dtype decomp warning in DEBUG=2 (#16300) sirhcmandGitHub 2026-05-20 19:08:48 -07:00
• ec547250ef don't use dtype vec for image idx (#16298) George HotzandGitHub 2026-05-20 18:45:13 -07:00
• 172f9493e1 move is_dtype_supported to renderer (#16226) sirhcmandGitHub 2026-05-20 18:19:37 -07:00
• d548f8d0f3 use clone instead of unique_const in allreduce [pr] (#16297) chenyuandGitHub 2026-05-20 18:58:47 -04:00
• 9e88b08f93 x86: don't use id (#16296) qazalandGitHub 2026-05-21 01:36:40 +03:00
• da07b28998 am: override smu 13_0_7 to 13_0_0 (#16292) sirhcmandGitHub 2026-05-20 15:14:30 -07:00
• beea4633fc UOp.clone [pr] (#16295) chenyuandGitHub 2026-05-20 17:47:49 -04:00
• a19fa2908f fix x86 nondeterminism (#16293) qazalandGitHub 2026-05-20 23:48:05 +03:00
• 58d58c1659 remove DEVECTORIZE (#16290) George HotzandGitHub 2026-05-20 13:25:49 -07:00
• 825f30bf18 llama: apply_grad saves memory (#16275) wozeparrotandGitHub 2026-05-20 16:14:06 -04:00
• a88feef40f hcq2: cleanups (#16278) nimlgenandGitHub 2026-05-20 21:48:50 +03:00
• a01d5918af fix: qlinearconv quant params (#16234) 3 people 2026-05-20 21:31:41 +03:00
• 19535df53c enable broadcasting in _shape (#16285) George HotzandGitHub 2026-05-20 11:21:51 -07:00
• 4dbe6a2ee7 remove _force_unique from Tensor init (#16277) chenyuandGitHub 2026-05-20 14:13:05 -04:00
• fe2d8d1ecf filter by base_class in pci_scan_bus on macOS (#16282) 3 people 2026-05-20 10:09:35 -07:00
• 1e0fffe256 fused ce llama kernel in UOps (#16263) qazalandGitHub 2026-05-20 13:45:28 +03:00
• e1715b3b92 extent jit const error to deviceless inputs (#16276) chenyuandGitHub 2026-05-20 02:02:45 -04:00
• 170b857da9 clean up deviceless const _buffer (#16274) chenyuandGitHub 2026-05-19 22:47:45 -04:00
• 7af7b6703a relax policy ASSERT_MIN_STEP_TIME to 3.2 (#16273) chenyuandGitHub 2026-05-19 22:29:09 -04:00
• 188d7ec15e clone can take device (#16271) chenyuandGitHub 2026-05-19 21:29:27 -04:00
• 361553c0a8 llama: match flat_llama with model_train (#16269) wozeparrotandGitHub 2026-05-19 20:25:56 -04:00
• da7414d6dc fix RUN_PICKLE and test it (#16272) George HotzandGitHub 2026-05-19 17:00:25 -07:00
• 55515747b7 Remove Ops.VCONST (#16267) George HotzandGitHub 2026-05-19 16:35:24 -07:00
• 7cdd9cbdeb PYTHONREMU: V_CVT_PK_BF8_F32 saturation (#16268) sirhcmandGitHub 2026-05-19 16:29:59 -07:00
• bb2a51f1ea fix mypy mockgpu and add tinygrad.renderer.isa to packages (#16265) sirhcmandGitHub 2026-05-19 13:45:03 -07:00