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

autogen-comgr-2

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

ci-deps

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

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

explicit-dev

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

gitea-test-ci

gl_dims

gldims

glm_flash

grad_outerworld

grok_x86_novec

group_div_rules

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-chat-template

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

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

onnx-cpu-count

outer_range

outerworld_work

pad_invalid

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

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-lp

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

view_after_const

view_in_codegen

viz_cbroadcast

warp_fun

wgpu-f16-packed

working_postopt

x86_moves

x86_numel

#1

#2

#3

#4

#5

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

• 406ec8240e hotfix: lin_fail_41 passes on my M3 Max geohot 2024-08-31 11:46:46 -07:00
• ad4b3b457f bump limit for test_llama_embedding_opt (#6332) Roelof van DijkandGitHub 2024-08-31 16:03:43 +02:00
• 72939901fc hotfix: ebs print kernel names geohot 2024-08-29 21:20:36 -07:00
• 365babe391 precompute early_reject [run_process_replay] (#6327) George HotzandGitHub 2024-08-29 18:26:24 -07:00
• 385904526f remove more rules [run_process_replay] (#6326) George HotzandGitHub 2024-08-29 16:27:10 -07:00
• 23081c4580 folding rules cleanup [run_process_replay] (#6325) George HotzandGitHub 2024-08-29 15:15:44 -07:00
• 56cd25e43f dearg consts [run_process_replay] (#6324) George HotzandGitHub 2024-08-29 15:00:22 -07:00
• 9b616cb33e HCQArgsState lifetime docs (#6323) nimlgenandGitHub 2024-08-30 00:31:49 +03:00
• 56b7fadc2f perf: skip type verify with -O (#6319) Roelof van DijkandGitHub 2024-08-29 22:47:51 +02:00
• 7a08b881ed st_fixup explicit UOp init [run_process_replay] (#6320) qazalandGitHub 2024-08-30 04:21:10 +08:00
• 539654fbe1 graph_rewrite complexity tests [run_process_replay] (#6317) qazalandGitHub 2024-08-30 03:39:08 +08:00
• 07942ef361 Proposal: Better UOps.SWIZZLE (#6309) qazalandGitHub 2024-08-29 20:39:48 +08:00
• 8c50ef8b7c start uop docs (#6291) qazalandGitHub 2024-08-29 20:22:39 +08:00
• dd4e5f1c8d process replay rewrite (#6284) qazalandGitHub 2024-08-29 20:08:27 +08:00
• 7de4eac8f7 add support and tests for nearest modes in interpolate, adapt uint8 bilinear to torch implementation (#6308) pedroandGitHub 2024-08-29 06:59:51 +02:00
• 638b4843da fix for metal ICB issue on M1/M2 [run_process_replay] (#6313) George HotzandGitHub 2024-08-28 21:31:14 -07:00
• cb61cfce24 feat: example and extra tweaks (#6310) wozeparrotandGitHub 2024-08-28 19:26:11 -07:00
• ea5b7910b7 AMD support gfx103x (#5926) wozeparrotandGitHub 2024-08-28 14:17:08 -07:00
• 94a72d44d2 update CI tests in extra with UOp AST (#6290) gswanggandGitHub 2024-08-28 12:26:50 -07:00
• 3517aa89d9 sdxl batched inference fixes (#6293) Tobias FischerandGitHub 2024-08-28 07:44:58 -04:00
• 85591bd1ae no need for functools here (#6303) Roelof van DijkandGitHub 2024-08-28 10:19:57 +02:00
• b1e5343133 nv better error msg for p2p failure (#6301) nimlgenandGitHub 2024-08-28 01:40:45 +03:00
• ac303146ca nv sure qmd addr less than 40bits (#6288) nimlgenandGitHub 2024-08-27 20:47:38 +03:00
• 5ed6c6ef3e hotfix: 220V 15A -> 220V 20A geohot 2024-08-27 10:20:43 -07:00
• ec34d9ee36 start benchmarking ast graph rewrite (#6297) qazalandGitHub 2024-08-27 23:18:44 +08:00
• 552fbd5527 update llm.c with UOp ast [run_process_replay] (#6296) qazalandGitHub 2024-08-27 20:04:54 +08:00
• 211bfb6d8a fixed batched clip computation (#6292) Tobias FischerandGitHub 2024-08-26 20:48:15 -04:00
• 3918f6eea0 refactor amd render_kernel (#6223) 3 people 2024-08-26 13:28:36 -03:00
• 3132449086 refactor _make_{cuda/clang}_dtype into render_vector_prefix (#6287) ignaciosicaandGitHub 2024-08-26 13:14:44 -03:00
• ab2714423b Add einsum tests (#6286) 3 people 2024-08-26 18:09:25 +02:00
• b76f0c875e lazy const fold idiv 1 (#6285) chenyuandGitHub 2024-08-26 10:29:59 -04:00
• af7c04ff57 Tensor.__floordiv__ (#6283) chenyuandGitHub 2024-08-26 09:43:40 -04:00
• d2f8eeed2e make [compare_schedule] the default [run_process_replay] (#6273) qazalandGitHub 2024-08-26 21:40:03 +08:00
• 067aeaeb2f single arange fusion with graph rewrite (#6160) qazalandGitHub 2024-08-26 18:18:16 +08:00
• b4381e9777 uop output_st is Optional [run_process_replay] (#6282) qazalandGitHub 2024-08-26 17:58:55 +08:00
• 1c0456af89 add UOps.SWIZZLE (#6271) qazalandGitHub 2024-08-26 16:08:51 +08:00
• 002f60b4c3 fix intel wmma flop counting, add flop counting tests for different tensor cores (#6192) CaltropHungertonandGitHub 2024-08-25 20:37:05 -05:00
• 331b0f5477 new clip gather (#6277) Tobias FischerandGitHub 2024-08-25 19:27:24 -04:00
• f0cc8ca5f2 generic st_fixup in scheduler graph rewrite [compare_schedule] (#6278) qazalandGitHub 2024-08-25 16:02:17 +08:00
• 70015bd89c move permute_reduces to uop movementops [run_process_replay] (#6272) qazalandGitHub 2024-08-25 15:25:51 +08:00
• b86907c6c7 UOp.const(x.dtype, y) -> x.const(y) [run_process_replay] (#6276) chenyuandGitHub 2024-08-24 21:39:50 -04:00
• 00282afa41 identity element of binary ops (#6275) chenyuandGitHub 2024-08-24 18:10:19 -04:00
• ee245b48a9 refactor reduceop swizzling (prep for UOps.SWIZZLE) [compare_schedule] (#6269) qazalandGitHub 2024-08-24 23:17:19 +08:00
• 3cf507ae7f remove extra.ops and LazyOp support from Kernel (#6267) gswanggandGitHub 2024-08-24 06:44:38 -07:00
• ccb05d8baa fixup neg tests [run_process_replay] (#6268) qazalandGitHub 2024-08-24 21:35:43 +08:00
• ea76b93814 migrate test_linearizer_dumb.py to UOp AST (#6241) gswanggandGitHub 2024-08-24 06:27:29 -07:00
• e44653e25a migrate test_linearizer_failures.py to UOp AST (#6240) 3 people 2024-08-24 06:26:58 -07:00
• 1b4ad982e5 share REDUCE_ALU in multi and schedule [run_process_replay] (#6266) qazalandGitHub 2024-08-24 21:16:38 +08:00
• 1dc6040877 migrate test_search.py to UOp AST (#6245) 3 people 2024-08-24 06:13:53 -07:00
• ae23540d6e refresh process replay schedule ref in reset.py (#6265) qazalandGitHub 2024-08-24 21:12:51 +08:00
• 7be5eede71 migrate test_linearizer_overflows.py to UOp AST (#6244) gswanggandGitHub 2024-08-24 06:10:29 -07:00
• 943ab97d24 fix Tensor.prod for multitensor (#6264) chenyuandGitHub 2024-08-24 08:52:24 -04:00
• bcb2f1caa3 init REDUCE_AXIS with BinaryOps (#6256) qazalandGitHub 2024-08-24 16:28:41 +08:00
• da5cf11859 fix acc init value for MUL (#6263) chenyuandGitHub 2024-08-23 23:19:44 -04:00
• a7bf20c7cd feat: updated tinybox docs (#6261) wozeparrotandGitHub 2024-08-23 18:27:46 -07:00
• 26498b322e add BEAM to external_benchmark_schedule.py geohot 2024-08-23 18:10:46 -07:00
• 53a73038e3 hotfix: TestGraphRewriteEfficiency.test_create_many_uops geohot 2024-08-23 15:51:57 -07:00
• 7c3ba3fa8a improve match stats + custom early reject [run_process_replay] (#6260) George HotzandGitHub 2024-08-23 15:28:57 -07:00
• 0b0a8829fb allowed_len early stop [run_process_replay] (#6257) George HotzandGitHub 2024-08-23 13:31:07 -07:00
• a18744188f more early reject [run_process_replay] (#6254) George HotzandGitHub 2024-08-23 12:16:44 -07:00
• 0d4887e9df use UOps.WMMA everywhere (#6255) qazalandGitHub 2024-08-24 03:03:26 +08:00
• 66d0b14a20 simpler CMPLT UOp _min_max [run_process_replay] (#6251) chenyuandGitHub 2024-08-23 10:36:16 -04:00
• 590c0922b6 Tensor.prod (#6250) chenyuandGitHub 2024-08-23 10:06:32 -04:00
• 78d6bd8b41 start graph rewrite in the scheduler (#6248) qazalandGitHub 2024-08-23 18:15:55 +08:00
• 75700edf73 minor bitcast touchup (#6246) chenyuandGitHub 2024-08-22 20:25:28 -04:00
• 4d40de867b remove redundant c1-(x+c2) rule [run_process_replay] (#6243) chenyuandGitHub 2024-08-22 16:45:49 -04:00
• 238896ca02 loooking into graph rewrite speed (#6239) George HotzandGitHub 2024-08-22 13:17:55 -07:00
• f62c4b3b5f remove redundant -(x*c) pattern [run_process_replay] (#6242) chenyuandGitHub 2024-08-22 16:11:02 -04:00
• e745e16441 remove UnaryOps.NEG (#6238) chenyuandGitHub 2024-08-22 14:21:39 -04:00
• 6c4ddd6260 hcq skip tests when no multidev (#6235) nimlgenandGitHub 2024-08-22 18:27:16 +03:00
• 08539f08b0 fix UOp repr with Variable in arg (#6236) chenyuandGitHub 2024-08-22 11:06:33 -04:00
• 3fc8203475 remove NEG from handwritten ast in tests (#6234) chenyuandGitHub 2024-08-22 09:06:59 -04:00
• 1c5ef5b793 format test_linearizer_failure (#6231) chenyuandGitHub 2024-08-21 21:10:56 -04:00
• 5cdec79469 simpler expand without dont_expand_args [run_process_replay] (#6230) George HotzandGitHub 2024-08-21 17:48:45 -07:00
• 78c94abe9c raise time limit for ci in test_profile_multidev_transfer (#6227) nimlgenandGitHub 2024-08-21 22:42:03 +03:00
• c74b318458 migrate test_linearizer.py to UOp AST, pt. 2 (#6228) gswanggandGitHub 2024-08-21 15:16:11 -04:00
• c3168952f0 wip: tracking pattern matcher [run_process_replay] (#6225) George HotzandGitHub 2024-08-21 11:57:26 -07:00
• a666450e4d UOp pattern x + x -> x * 2 (#6224) chenyuandGitHub 2024-08-21 12:06:19 -04:00
• c9a9631818 no UnaryOps.NEG in generated UOp patterns (#6209) chenyuandGitHub 2024-08-21 11:08:22 -04:00
• 3b8cc5a3e0 more multireduce tests prep for neg removal [run_process_replay] (#6220) qazalandGitHub 2024-08-21 17:45:24 +08:00
• 86c036f0d3 reorder uops.py [run_process_replay] (#6219) qazalandGitHub 2024-08-21 16:39:55 +08:00
• f03e5a4b3b test_multireduce const has a shape (#6218) qazalandGitHub 2024-08-21 16:02:45 +08:00
• 911bf7216c remove unused match rules [run_process_replay] (#6217) George HotzandGitHub 2024-08-21 00:16:04 -07:00
• 2c42e9c2c6 faster rewrite, no folder in expand/reduce [run_process_replay] (#6216) George HotzandGitHub 2024-08-20 23:36:58 -07:00
• 16f420f7a7 split full_graph_rewrite and linearize_uop [run_process_replay] (#6215) George HotzandGitHub 2024-08-20 20:12:33 -07:00
• 9faf205601 CIFAR trainer + various bugfixes / improvements (#6146) George HotzandGitHub 2024-08-20 16:58:46 -07:00
• 296368f0dd Revert "delete arg from cast [run_process_replay] (#6202)" (#6214) George HotzandGitHub 2024-08-20 16:45:30 -07:00
• 89c4cffd86 nv fix size in SET_SEMAPHORE_A (#6213) nimlgenandGitHub 2024-08-21 01:47:10 +03:00
• ec52a09393 delete arg from cast [run_process_replay] (#6202) qazalandGitHub 2024-08-21 05:06:16 +08:00
• 7376b67e36 extra/gemm/triton_nv_matmul: fix Program arguments (#6212) Francis LamandGitHub 2024-08-20 14:05:38 -07:00
• 4bb98d8882 Fix track_running_stats in batchnorm (#6200) madt2709andGitHub 2024-08-20 14:01:22 -07:00
• d9c62a33c3 add cifar to datasets.py (#6210) George HotzandGitHub 2024-08-20 11:42:49 -07:00
• a5d79688db fix indexing out of bounds (#6208) George HotzandGitHub 2024-08-20 11:34:56 -07:00
• 4451bcaf95 update test_arange test_llama_embedding_opt (#6207) chenyuandGitHub 2024-08-20 13:58:43 -04:00
• e4bb63c1be Refactor amd kernel prefix (#6205) ignaciosicaandGitHub 2024-08-20 14:37:36 -03:00
• 074cf780dd add option to only benchmark schedule [run_process_replay] (#6204) qazalandGitHub 2024-08-20 21:51:27 +08:00
• 8fd8b970b0 update URL to eval cases from recent MLPerf file movements (#6201) Francis LataandGitHub 2024-08-20 08:43:13 -04:00
• 0e6f057eae migrate test_linearizer.py to UOP AST (pt. 1) (#6150) 3 people 2024-08-20 03:02:20 -04:00
• 10330a41c7 add CMPNE tests in test_uops (#6196) chenyuandGitHub 2024-08-19 19:41:21 -04:00
• 21d6739237 remove UnaryOps.NEG from lazy.py (#6193) chenyuandGitHub 2024-08-19 18:41:28 -04:00