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

• 11d62668a3 refactor ast ops dtype access [run_process_replay] (#6093) qazalandGitHub 2024-08-16 00:13:33 +08:00
• 9ef82e1f2b UOp pattern DEFINE_VAR with min==max is also CONST (#6095) chenyuandGitHub 2024-08-15 12:09:44 -04:00
• a41c9dd12c test py.typed as a package (#6094) chenyuandGitHub 2024-08-15 11:19:08 -04:00
• 25dffb2079 kernel.py more typing [run_process_replay] (#6092) qazalandGitHub 2024-08-15 22:59:24 +08:00
• 4d38fec8c1 rename lazyops to parents [run_process_replay] (#6091) qazalandGitHub 2024-08-15 22:27:32 +08:00
• 5accfe26a0 rewrite bool ADD to OR and MUL to AND (#6084) chenyuandGitHub 2024-08-15 10:11:57 -04:00
• b765996d54 hcq remove offset from progs (#6090) nimlgenandGitHub 2024-08-15 17:02:54 +03:00
• df03dca6e3 move % inside UOp mod_folding and remove deprecated tests (#6085) chenyuandGitHub 2024-08-14 23:25:10 -04:00
• c6e117c899 add a single py.typed (#6083) George HotzandGitHub 2024-08-14 17:31:46 -07:00
• 2bf7b56485 minor test fixups from the AST is UOp diff (#6081) qazalandGitHub 2024-08-15 04:58:04 +08:00
• 95aa6d8ccd remove redundant x/c pattern [run_process_replay] (#6082) chenyuandGitHub 2024-08-14 16:57:39 -04:00
• a61cb1ff7c move mod mod pattern into generic mod folding (#6077) chenyuandGitHub 2024-08-14 16:24:21 -04:00
• 64563abc90 add LSTMCell to nn (#6080) George HotzandGitHub 2024-08-14 12:08:42 -07:00
• 6b3112d525 fix qcom process_replay for kernel diff (#6079) chenyuandGitHub 2024-08-14 15:05:49 -04:00
• 2fe9d62451 increase test_recursive_add time from 1s to 2s (#6078) chenyuandGitHub 2024-08-14 13:52:02 -04:00
• 7ab531aede autogen cleanup (#6064) nimlgenandGitHub 2024-08-14 20:20:35 +03:00
• de773b593e remove redundant div gcd patterns [run_process_replay] (#6076) chenyuandGitHub 2024-08-14 13:18:28 -04:00
• 2dc586ffe5 Shape change bitcast for more dtypes (#6047) 3 people 2024-08-14 18:03:34 +01:00
• 83a2543c74 spec for in order LOAD/STORE indexing (#6073) qazalandGitHub 2024-08-15 00:18:00 +08:00
• 5048f9a4d5 test linearizer failure 49 (#6074) chenyuandGitHub 2024-08-14 11:29:10 -04:00
• 30035df5a4 add metal process replay back (#6068) qazalandGitHub 2024-08-14 17:29:56 +08:00
• 518c022c29 feat: tag 0.9.2 (#6067) v0.9.2 wozeparrotandGitHub 2024-08-13 16:15:36 -07:00
• 97c3563109 hotfix: clamp in docs geohot 2024-08-13 16:04:25 -07:00
• e039b2a920 add Tensor.clamp and fix bool loading (#6069) George HotzandGitHub 2024-08-13 15:26:40 -07:00
• 1782e4f64d use div folding to do lt folding (#6065) chenyuandGitHub 2024-08-13 16:59:05 -04:00
• e3af273fa1 touchup cl_errors (#6058) chenyuandGitHub 2024-08-13 13:06:59 -04:00
• 9145ad52ff revert UOps eq, this needs to be isolated in realize.py (#6063) qazalandGitHub 2024-08-13 23:02:34 +08:00
• fa84e6ec48 init hcq args state (#6046) nimlgenandGitHub 2024-08-13 17:11:58 +03:00
• 9d2ea94fe9 temp: disable process replay on metal (#6062) qazalandGitHub 2024-08-13 21:31:55 +08:00
• 18192079a9 Apply transcendental rewrite rules only if required by backend (#6061) andredapratoandGitHub 2024-08-13 01:38:45 -04:00
• 6e3eb50fd1 added fix and reg tests (#6060) Tobias FischerandGitHub 2024-08-12 21:00:48 -04:00
• 45bd667a78 rewrite pyint after first rewrite [run_process_replay] (#6059) chenyuandGitHub 2024-08-12 19:18:13 -04:00
• 2ac80576e4 remove BufferOps from log_lazybuffer (#6057) qazalandGitHub 2024-08-13 07:06:47 +08:00
• dccca7f227 test: uop and lazyop have the same compare (#6053) qazalandGitHub 2024-08-13 05:33:19 +08:00
• 8c501272f3 proposal: MetaOps.EXT (#6054) qazalandGitHub 2024-08-13 05:29:29 +08:00
• 059cf2a90d feat: autogen from kernel register offset headers (#6056) wozeparrotandGitHub 2024-08-12 14:08:35 -07:00
• 3f2d24a6ec test_failure_48 for wrong truncation in idx on NV (#6055) chenyuandGitHub 2024-08-12 16:17:42 -04:00
• 6ed9711898 UOps pattern (x%c)+(x//c)*c = x (#6051) chenyuandGitHub 2024-08-12 14:58:48 -04:00
• 71c5901fc1 refactor ast arg and op [compare_schedule] (#6052) qazalandGitHub 2024-08-13 02:51:00 +08:00
• dc2617bffd feat: use more correct reg for local dims (#6048) wozeparrotandGitHub 2024-08-12 11:15:37 -07:00
• 529832d223 refactor ast creation [compare_schedule] (#6050) qazalandGitHub 2024-08-13 02:15:11 +08:00
• 8f787785d9 fix openpilot benchmark (#6049) nimlgenandGitHub 2024-08-12 21:12:32 +03:00
• 777d6b3349 Fix compile error for max with inline const (#5840) ignaciosicaandGitHub 2024-08-12 12:40:39 -03:00
• e9024c691f metal raise when command queue is not created (#6044) nimlgenandGitHub 2024-08-12 18:30:37 +03:00
• 164ca5632e split tensor core tests (#6041) ignaciosicaandGitHub 2024-08-12 10:42:02 -03:00
• 7ce716b3a0 bigint -> pyint [run_process_replay] (#6040) chenyuandGitHub 2024-08-12 09:12:23 -04:00
• 059dd35985 minor UOps.RANGE ordering cleanup [run_process_replay] (#6039) qazalandGitHub 2024-08-12 20:33:26 +08:00
• a00994b423 Lowerer Multireduce Uopgraph (#6007) TimmyandGitHub 2024-08-12 05:16:07 -07:00
• bb653fa0a5 use dict for UOp parents (#6036) qazalandGitHub 2024-08-12 20:06:45 +08:00
• 7d1f118731 use assertIs in test_schedule (#6035) qazalandGitHub 2024-08-12 00:19:18 +08:00
• b918e3c255 cache assert_equiv_uops (#6033) qazalandGitHub 2024-08-11 17:17:05 +08:00
• 8d108f65a4 add cast to TC=2 (#6032) George HotzandGitHub 2024-08-10 18:47:12 -07:00
• 14b613e281 add STEPS to beautiful_mnist geohot 2024-08-10 15:23:44 -07:00
• 1b3443902c don't use tgmath with clang (#6029) George HotzandGitHub 2024-08-10 13:58:19 -07:00
• e05a1d6113 string -> fstring (#6028) gswanggandGitHub 2024-08-10 16:28:31 -04:00
• 5820940d98 more relax rtol for test_arange_fuse_grouped_children (#6027) chenyuandGitHub 2024-08-10 16:10:03 -04:00
• d82370f6ef docs: fix broken links and update is_floating_point (#6023) chenyuandGitHub 2024-08-10 15:58:48 -04:00
• d58ae17771 Cleanup cstlye render_const [run_process_replay] (#6024) gswanggandGitHub 2024-08-10 15:58:02 -04:00
• 10374a2741 relax rtol for test_arange_fuse_grouped_children (#6026) chenyuandGitHub 2024-08-10 15:49:11 -04:00
• cf7d3c1eb8 fix tests locally on metal (#6025) George HotzandGitHub 2024-08-10 12:36:22 -07:00
• e6c7c3e499 update pylint path to check indent/space for all (#6022) chenyuandGitHub 2024-08-10 14:41:09 -04:00
• cfb04c67d1 run unit tests separate from others (and only once) (#6020) George HotzandGitHub 2024-08-10 11:17:56 -07:00
• 8302dd6ea4 remove noqa: E501 from transcendental geohot 2024-08-10 10:30:05 -07:00
• 350276e947 simpler device_from_env [run_process_replay] (#6015) chenyuandGitHub 2024-08-10 13:17:46 -04:00
• ee3b015407 ELF loader strtab fix and tests (#6011) uuuvnandGitHub 2024-08-10 20:13:16 +03:00
• 54e176fb4f Ignore non-computational backends when overwriting the default (#5770) Jun ZhangandGitHub 2024-08-11 00:23:29 +08:00
• 3ef2788c4f hotfix: run the entire test_conv_bw schedule (#6014) qazalandGitHub 2024-08-10 22:55:41 +08:00
• 0e62076cf5 more process replay cleanups (#6013) qazalandGitHub 2024-08-10 22:29:10 +08:00
• 266afad8ed hotfix: skip schedule capture in benchmarks (#6012) qazalandGitHub 2024-08-10 22:13:53 +08:00
• 63a8bc29d4 addition divisor in UOp div_folding (#6002) chenyuandGitHub 2024-08-09 20:09:05 -04:00
• 52a74e1d6f recursive div_folding to simplify logic (#6008) chenyuandGitHub 2024-08-09 19:23:06 -04:00
• a4ec4e890a merge mul div pattern into div_folding (#6006) chenyuandGitHub 2024-08-09 18:49:36 -04:00
• 5961faa4be minor change to UOp div_fold (#6004) chenyuandGitHub 2024-08-09 17:09:59 -04:00
• 7373b05ee8 assert conv bw reduceops merge [compare_schedule] (#6001) qazalandGitHub 2024-08-10 00:29:56 +08:00
• b67d521a07 assert test_conv_bw correctness (#6000) qazalandGitHub 2024-08-09 23:30:36 +08:00
• ce066fd754 nv do not recalc mv_address (#5998) nimlgenandGitHub 2024-08-09 17:16:34 +03:00
• a833f1a735 scheduler process replay with [compare_schedule] (#5997) qazalandGitHub 2024-08-09 21:58:22 +08:00
• 24c7c41ce0 diff LazyBuffer schedules in process replay (#5996) qazalandGitHub 2024-08-09 19:16:43 +08:00
• d269bc95fa faster tinychat (#5993) wozeparrotandGitHub 2024-08-08 19:16:26 -07:00
• 1f1eb46af6 more failed simplified UOp div test case (#5992) chenyuandGitHub 2024-08-08 18:39:25 -04:00
• 94dc61aa1f typeguard fixes for beautiful-mnsit JIT=2 METAL=1 [run_process_replay] (#5984) gswanggandGitHub 2024-08-08 14:53:33 -07:00
• c3e1ae2535 add failed simplified UOp div test case (#5990) chenyuandGitHub 2024-08-08 17:37:48 -04:00
• 38d5eecc68 hcq profiler support args (#5989) nimlgenandGitHub 2024-08-09 00:18:36 +03:00
• 45b1761175 smaller test_llama_embedding + assert correctness (#5986) qazalandGitHub 2024-08-09 03:11:29 +08:00
• 8c99bdab08 More Multireduce Tests (#5968) TimmyandGitHub 2024-08-08 12:04:08 -07:00
• 3c0924cac4 UOp int alu patterns match all int (#5987) chenyuandGitHub 2024-08-08 14:50:58 -04:00
• df44a4e861 Make vectorization of CONST explicit (#5322) 4 people 2024-08-08 10:59:05 -07:00
• 62c77a2831 trim const in UOp div_folding (#5982) chenyuandGitHub 2024-08-08 12:49:05 -04:00
• e6d41b0ce7 hotfix: adjust test_backward_pass_diamond_model thresholds (#5981) qazalandGitHub 2024-08-09 00:20:53 +08:00
• 08d22066ee simplify ALU vmin==vmax fold (#5962) gswanggandGitHub 2024-08-08 08:29:16 -07:00
• c9b4602854 no load in INITMLPERF (#5957) Elias WahlandGitHub 2024-08-08 17:28:24 +02:00
• 183c4c91a3 fix non-jitted transfers in profile (#5980) nimlgenandGitHub 2024-08-08 17:58:08 +03:00
• 76eca0d27e nv fix host mem mappings (#5979) nimlgenandGitHub 2024-08-08 17:03:44 +03:00
• e89eff11a6 amd raise when not supported arch (#5978) nimlgenandGitHub 2024-08-08 14:46:14 +03:00
• bc55c8a30e pmatmul example + GB/s bugfix [run_process_replay] (#5974) George HotzandGitHub 2024-08-07 22:32:11 -07:00
• c5baa3d66b hotfix: don't run OOM test in CI geohot 2024-08-07 22:19:29 -07:00
• 859d0e4709 UOp simplify (x+c0)*c1 -> x*c1+c0*c1 (#5973) chenyuandGitHub 2024-08-07 21:25:22 -04:00
• 97d708252a remove realize from threefry (#5969) wozeparrotandGitHub 2024-08-07 15:08:49 -07:00
• bf8ec23b00 hotfix: contiguous on precompute_freqs_cis geohot 2024-08-07 14:40:04 -07:00
• d3e427c8d9 fix sqlite3 locks (#5971) wozeparrotandGitHub 2024-08-07 14:38:19 -07:00