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

• 38bc38cdff fix llama example quantize (#4699) chenyuandGitHub 2024-05-23 15:35:26 -04:00
• 532c9e08e3 proposal: PHI nodes in TC shouldn't have children inside the loop (#4694) qazalandGitHub 2024-05-24 03:11:26 +08:00
• afb426acaf docs: gather, cat, stack, repeat, squeeze, unsqueeze (#4697) chenyuandGitHub 2024-05-23 14:20:19 -04:00
• ce46a7e83f raise CompileError in metal if newLibraryWithSource_options_error_ fails (#4695) chenyuandGitHub 2024-05-23 12:52:46 -04:00
• 871a3292f4 Refactors linearizer acc to a Dict (#4675) 3 people 2024-05-23 09:05:23 -07:00
• 72560e30fe add CACHELEVEL=0 to tinybox green GEMM BEAM (#4693) chenyuandGitHub 2024-05-22 23:59:50 -04:00
• af56f0e68a fix HSA/KFD load for system-wide installation (#4218) 3 people 2024-05-23 12:33:21 +09:00
• 12339f6564 disable cuda test in ci (#4630) 3 people 2024-05-23 06:23:32 +03:00
• 9a9963ba7b Remove uops deepcopy from PTX (#4671) 3 people 2024-05-23 05:14:17 +02:00
• 47aba47f64 update Torch.gather api (#4692) chenyuandGitHub 2024-05-22 21:54:06 -04:00
• 792a494eb8 fix various examples (#4691) chenyuandGitHub 2024-05-22 20:43:21 -04:00
• 30b07f3c5d reduce ops (#4690) wozeparrotandGitHub 2024-05-22 23:20:56 +00:00
• a46be6cfef docs for transpose (#4689) chenyuandGitHub 2024-05-22 18:44:33 -04:00
• 86da83f86d move movement op docs (#4688) chenyuandGitHub 2024-05-22 18:09:14 -04:00
• 498cf3e7e0 fuzzer path search for DEFINE_ACC (#4656) qazalandGitHub 2024-05-23 05:50:01 +08:00
• f11a81f707 isolated test for BEAM=2 llama wrong uops toposort (#4687) qazalandGitHub 2024-05-23 05:47:37 +08:00
• 6020595eb0 more tensor.py docs (#4686) wozeparrotandGitHub 2024-05-22 21:28:26 +00:00
• 721f9f6acf test/external/verify_kernel: fix LOGKERNS variable name in comments (#4685) Francis LamandGitHub 2024-05-22 14:08:40 -07:00
• f8f97562e0 remove File Specific Variables from env_vars.md (#4684) chenyuandGitHub 2024-05-22 17:00:14 -04:00
• 225dcab3be prepend _ to broadcast_shape and deepwalk (#4683) chenyuandGitHub 2024-05-22 16:39:05 -04:00
• c5f5755328 correctness test for multireduce nested locals (#4682) qazalandGitHub 2024-05-23 00:35:35 +08:00
• bc9be39dec set timeout in search _try_compile_linearized_w_idx (#4677) chenyuandGitHub 2024-05-22 12:30:31 -04:00
• d12d412e8b revert uops dtype in pattern matcher (#4681) qazalandGitHub 2024-05-22 19:45:51 +08:00
• acc0039cfc Resume fix + scheduler for non weight decay params (#4679) Elias WahlandGitHub 2024-05-22 01:38:13 +02:00
• 0f21aa0416 example kernel that triggers Memory access fault for resnet on red (#4678) chenyuandGitHub 2024-05-21 18:59:36 -04:00
• 5f84cbb5df keep UOps.CAST in PHI-GEP fold for unmatching dtypes (#4674) qazalandGitHub 2024-05-22 02:59:49 +08:00
• 458a3961eb catch compile errors in uops tests (#4672) qazalandGitHub 2024-05-21 17:20:35 +08:00
• 00432496d7 feat: tinyboxgreen (#4366) wozeparrotandGitHub 2024-05-20 19:39:34 -07:00
• de733d73cf Multireduce Linearizer Tests (#4665) 3 people 2024-05-20 16:43:25 -07:00
• 5e3fbbb33e llama3 example add manual seed and log seed (#4667) chenyuandGitHub 2024-05-20 19:09:57 -04:00
• 8c99cc17f5 remove link to old adding_new_accelerators.md (#4666) chenyuandGitHub 2024-05-20 19:05:23 -04:00
• c4089d169f update BEAM_LOCAL_MAX to 1024 (#4664) chenyuandGitHub 2024-05-20 18:06:32 -04:00
• 704cb1d8a0 fix conversation.py quantize (#4663) chenyuandGitHub 2024-05-20 17:36:37 -04:00
• ae861325ce update llama sample for mac 32 input buffer limit (#4662) chenyuandGitHub 2024-05-20 17:23:39 -04:00
• 993091adfa loss scaler + nan fixes (#4661) Elias WahlandGitHub 2024-05-20 23:08:35 +02:00
• b33c827aed UOps.RANGE toposort spec (#4660) qazalandGitHub 2024-05-21 04:38:20 +08:00
• 0d9e623d83 consolidate uops tests (#4659) qazalandGitHub 2024-05-21 02:42:31 +08:00
• 1e7b7b2c3c Fix flop coutning for mulacc (#4640) Szymon OżógandGitHub 2024-05-20 18:06:00 +02:00
• b144d4b460 new llama3 example (#4576) wozeparrotandGitHub 2024-05-19 22:42:23 -07:00
• c9f7f2da70 nv hcq bind api (#4629) nimlgenandGitHub 2024-05-19 23:17:10 +03:00
• d308f4fa9a correctly insert UOps.END* in fuzz result (#4653) qazalandGitHub 2024-05-20 02:10:28 +08:00
• 456aa0b656 update test_search kernel count (#4652) chenyuandGitHub 2024-05-19 13:54:52 -04:00
• 954718e6bf reorder DEFINE_GLOBAL in fuzz_uops (#4651) qazalandGitHub 2024-05-20 01:51:31 +08:00
• 967e35f8b8 fix(beam): GlobalCounters kernel count increasing when clearing l2 (#4598) 3 people 2024-05-19 19:03:47 +02:00
• 4753283221 LOOP -> RANGE (#4650) George HotzandGitHub 2024-05-19 06:40:20 -07:00
• 286b4dbdf2 compile raise CompileError and skip only RuntimeError in multiprocess… (#4646) chenyuandGitHub 2024-05-19 00:25:25 -04:00
• 8a0d1ca7bb CI test timeout 20 min -> 10 min (#4645) chenyuandGitHub 2024-05-18 13:58:28 -04:00
• b0cb02f719 uops fuzzing infra (#4641) qazalandGitHub 2024-05-19 01:19:57 +08:00
• bf8f855838 assert kernel counts in unsupported fusions (#4643) qazalandGitHub 2024-05-19 01:14:37 +08:00
• a5204fe89d refactor UOps.CONST (#4639) qazalandGitHub 2024-05-18 15:07:36 +08:00
• d0a2d40df3 root cause fix for UOps.CONST bad args (#4638) qazalandGitHub 2024-05-18 14:15:25 +08:00
• 9b464e34ea increase speed of uops (#4637) George HotzandGitHub 2024-05-17 21:04:39 -07:00
• b74cc1d01a uops cleanup (#4634) George HotzandGitHub 2024-05-17 20:02:38 -07:00
• 07b350a8f4 new uops is an actual graph (#4560) George HotzandGitHub 2024-05-17 18:00:18 -07:00
• daf57af3eb move tc to renderers (#4631) nimlgenandGitHub 2024-05-18 00:36:29 +03:00
• d70988dddf add blob and raw=true for image in docs showcase (#4632) chenyuandGitHub 2024-05-17 16:57:15 -04:00
• 10cf8e459b hcq update queue in place (#4626) nimlgenandGitHub 2024-05-17 22:18:20 +03:00
• ca1df20fa9 benchmark name fix - resnet eval is on eval data (#4628) chenyuandGitHub 2024-05-17 12:56:12 -04:00
• c86adabe15 time with real global buffers in search (#4621) chenyuandGitHub 2024-05-17 12:36:23 -04:00
• e5d4e6a8aa BEAM=2 in green CI for 100 TFLOPS (#4624) chenyuandGitHub 2024-05-16 23:28:28 -04:00
• b3dd885ffb cleanup double import from tinygrad.device in tensor.py (#4620) chenyuandGitHub 2024-05-16 14:21:22 -04:00
• 639ea5b0f2 Metal linearizer failure 22 is flaky not just on CI (#4617) uuuvnandGitHub 2024-05-16 18:31:23 +03:00
• f3f2b96583 pick schedule tests from external_test_opt (#4615) qazalandGitHub 2024-05-16 20:43:41 +08:00
• 13200c6894 check simple_pads in all views (#4614) qazalandGitHub 2024-05-16 19:34:39 +08:00
• 0b464df605 base change scheduling spec (#4613) qazalandGitHub 2024-05-16 18:30:49 +08:00
• 65f7e3b3ab nv setup constbuf4 (#4511) nimlgenandGitHub 2024-05-16 10:42:35 +03:00
• 04f2327ca3 fix abs of diff of uint (#4411) chenyuandGitHub 2024-05-15 18:39:11 -04:00
• 2119e0456d redo simpler abs and sign (#4611) chenyuandGitHub 2024-05-15 18:19:46 -04:00
• eb9689336e nv mockgpu (#4600) nimlgenandGitHub 2024-05-15 23:46:08 +03:00
• 3c11ca452e skip CLANG test casts between double and half for now (#4609) chenyuandGitHub 2024-05-15 16:17:06 -04:00
• 8694eeb16d Revert "simpler abs and sign (#4606)" (#4608) chenyuandGitHub 2024-05-15 15:46:33 -04:00
• a5e157f663 simpler abs and sign (#4606) chenyuandGitHub 2024-05-15 14:33:09 -04:00
• 5ba611787d move image into tensor.py. delete features (#4603) George HotzandGitHub 2024-05-15 10:50:25 -07:00
• 36d2ac603e allbufs are base (#4605) qazalandGitHub 2024-05-16 01:46:37 +08:00
• 067ff719c2 fix comment for Tensor.swish (#4604) chenyuandGitHub 2024-05-15 13:32:47 -04:00
• cd4d7e18c7 _recurse_lb small cleanup (#4601) qazalandGitHub 2024-05-16 00:10:42 +08:00
• 662bca8134 Split UnaryOps.CAST into CAST and BITCAST (#4487) Ahmed HarmoucheandGitHub 2024-05-15 17:43:31 +02:00
• 53d082a2aa move memory into schedule (#4597) George HotzandGitHub 2024-05-15 07:54:20 -07:00
• a4a23c40a0 test masked assign views (#4599) qazalandGitHub 2024-05-15 20:06:48 +08:00
• ff64bcab69 move graph/search to engine (#4596) George HotzandGitHub 2024-05-14 23:12:59 -07:00
• afa9753d39 ruff cleanup (#4594) George HotzandGitHub 2024-05-14 21:16:14 -07:00
• 7f009cf9fa split arange threefry (#4590) wozeparrotandGitHub 2024-05-14 21:10:22 -07:00
• 9425973bc7 docs cleanup and move (#4593) George HotzandGitHub 2024-05-14 20:44:59 -07:00
• fd02ab1e8b move disassemblers and openpilot (#4592) George HotzandGitHub 2024-05-14 19:30:02 -07:00
• 2b0ee74bb6 lshift and rshift (#4591) chenyuandGitHub 2024-05-14 19:16:31 -04:00
• 45e7400e3c start amd cleanup (#4583) nimlgenandGitHub 2024-05-14 22:59:59 +03:00
• a65c8de735 move .half() llama freq_cis to the end of sin and cos (#4587) chenyuandGitHub 2024-05-14 15:00:18 -04:00
• 9aa5e02229 update llmc export (#4584) qazalandGitHub 2024-05-15 02:18:38 +08:00
• 355e1c135c pad fusion tests (#4570) qazalandGitHub 2024-05-15 01:34:46 +08:00
• 7afca52796 replace pow in LAMB by tracking b1**t and b2**t per step (#4582) chenyuandGitHub 2024-05-14 13:08:22 -04:00
• 9b02aef45a remove rhip (#4579) nimlgenandGitHub 2024-05-14 17:58:19 +03:00
• 5eb81ff764 Fix speed compare script (#4581) Szymon OżógandGitHub 2024-05-14 16:47:03 +02:00
• 2131556c2c amd mockgpu (#4535) nimlgenandGitHub 2024-05-14 14:28:04 +03:00
• 089eeec271 setitem in-place operator tests (#4577) geohotstanandGitHub 2024-05-14 13:28:02 +08:00
• 0fa57b8ce9 raise error if setitem tensors have requires_grad (#4575) chenyuandGitHub 2024-05-13 18:56:47 -04:00
• f7d08bd454 feat: add acc_dtype to einsum (#4571) Filip BrzekandGitHub 2024-05-13 20:02:07 +02:00
• d97d5a7689 Optimize PTX gated loads index calculation (#4304) 4 people 2024-05-13 19:14:01 +02:00
• c67b70ca67 small scheduler refactor (#4569) qazalandGitHub 2024-05-13 15:47:39 +08:00
• 77aa8659f5 use assign_targets in LazyOp creation (#4568) qazalandGitHub 2024-05-13 15:24:35 +08:00
• b0fa97e176 assert error detail in test_assign (#4567) qazalandGitHub 2024-05-13 14:56:05 +08:00