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

• 581397110f nv: use classes in GSP_IP (#11163) nimlgenandGitHub 2025-07-10 17:47:12 +03:00
• 705de6b8a6 nv: parse sizes of ctx buffers (#11161) nimlgenandGitHub 2025-07-10 17:46:48 +03:00
• dcc9704b6b viz: profile RewriteSteps in TINY device (#11125) qazalandGitHub 2025-07-10 17:45:57 +03:00
• 32117402dd metal: fix incorrect _free on interpreter exit (#11158) Pyry KovanenandGitHub 2025-07-10 14:01:30 +03:00
• 3d610f6d2b viz: small ui cleanup (#11157) qazalandGitHub 2025-07-10 11:43:36 +03:00
• 7db07e5f2c don't narrow range of CAST on bool/unsigned (#11156) chenyuandGitHub 2025-07-09 22:20:09 -04:00
• e154a66f43 unroll axis 0 in tensor core (#11155) George HotzandGitHub 2025-07-09 17:28:23 -07:00
• b7742ad9e4 migrate to string swizzle [pr] (#11154) George HotzandGitHub 2025-07-09 16:57:53 -07:00
• 4156baee93 break swizzle into three chunks [pr] (#11153) George HotzandGitHub 2025-07-09 15:30:34 -07:00
• ca2dc95433 swizzle in tc can't be none [pr] (#11152) George HotzandGitHub 2025-07-09 14:44:23 -07:00
• 53ae153404 tc should be in opt (#11148) George HotzandGitHub 2025-07-09 14:12:21 -07:00
• 6697d0089d initial gfx950 kfd support (#11151) wozeparrotandGitHub 2025-07-09 13:45:16 -07:00
• 262054be52 gfx950 tc support (#11150) George HotzandGitHub 2025-07-09 13:30:42 -07:00
• b6981404ed memory: use page shifts in memory manager (#11149) nimlgenandGitHub 2025-07-09 22:05:00 +03:00
• 5c1d215b41 viz: add Graph stream (#11144) qazalandGitHub 2025-07-09 20:56:46 +03:00
• 22305260e0 move tc to tc.py [pr] (#11147) George HotzandGitHub 2025-07-09 10:55:56 -07:00
• 2893feb9f6 cleanups for kernel.py (#11143) George HotzandGitHub 2025-07-08 18:10:25 -07:00
• b11ca104e9 axis cleanups [pr] (#11142) George HotzandGitHub 2025-07-08 17:07:26 -07:00
• 7ce9e45474 mypy onnx_parser (#11141) chenyuandGitHub 2025-07-08 19:50:28 -04:00
• a1b8f3e64f delete info from kernel [pr] (#11139) George HotzandGitHub 2025-07-08 15:53:13 -07:00
• 359bed74f8 axis type tracking [pr] (#11137) George HotzandGitHub 2025-07-08 14:16:25 -07:00
• dada3f5bf3 skip some new onnx tests (#11135) chenyuandGitHub 2025-07-08 16:12:48 -04:00
• ffcc557986 lint onnx and onnx_parser (#11134) chenyuandGitHub 2025-07-08 15:28:35 -04:00
• 3238d21cd1 add finalized to kernel [pr] (#11132) George HotzandGitHub 2025-07-08 11:06:17 -07:00
• 289a411f5f hotfix: remove unused GBARRIER, CONTIGUOUS color is GBARRIER geohot 2025-07-08 10:31:06 -07:00
• 43650169f4 nv: switch headers to 570.144 to match gsp (#11131) nimlgenandGitHub 2025-07-08 20:29:06 +03:00
• 790b05ab12 [pr] Unify CONTIGUOUS and GBARRIER (#11121) quortusandGitHub 2025-07-08 19:27:23 +02:00
• b516fe71b4 nv: return real struct in _alloc_boot_struct (#11130) nimlgenandGitHub 2025-07-08 20:04:43 +03:00
• 348ab6c30f rough sketches of some apps geohot 2025-07-08 09:43:34 -07:00
• 3dfc0ff887 move cpu_profile and shared ProfileEvents from device.py to helpers [pr] (#11126) qazalandGitHub 2025-07-08 12:14:03 +03:00
• 397826f0b4 add a test for 1B llm (#11124) George HotzandGitHub 2025-07-07 18:47:25 -07:00
• f7d4638e05 start LLM app, tons of clean up required. target is 200 line ollama (#11068) George HotzandGitHub 2025-07-07 17:09:46 -07:00
• 341a686799 Tensor.diagonal (#11122) chenyuandGitHub 2025-07-07 16:21:26 -04:00
• 584fd6af5a Fix division by zero and mask bug in add views (#11088) 3 people 2025-07-07 19:05:47 +02:00
• 71377cd233 nv: parse falcon app descs (#11118) nimlgenandGitHub 2025-07-07 18:14:14 +03:00
• 9a573a1d99 nv: finalize nvdev (#11117) nimlgenandGitHub 2025-07-07 16:31:59 +03:00
• fa59c05282 nv: import flags from system (#11115) nimlgenandGitHub 2025-07-07 14:46:49 +03:00
• a1a146a499 adding enable_gqa in SDPA (#11097) 3 people 2025-07-07 08:25:33 +02:00
• b73e89110e nv: align allocations for perf (#11114) nimlgenandGitHub 2025-07-06 22:32:11 +03:00
• 7468959f4b Tensor.argsort (#11112) chenyuandGitHub 2025-07-06 13:56:35 -04:00
• b7af9cf849 clean svd tests, set full_matrices false in torch backend (#11113) kevvzandGitHub 2025-07-06 10:55:49 -07:00
• a556f50668 viz: small ui fixes (#11110) qazalandGitHub 2025-07-06 17:05:36 +03:00
• ba88ec3ad0 pipe linalg svd to torch (#11109) chenyuandGitHub 2025-07-06 08:37:25 -04:00
• 845a4d32bc Tensor.diag (#11108) chenyuandGitHub 2025-07-05 23:03:02 -04:00
• 4905af4ae0 remove invalid int div test (#11106) ttomsaandGitHub 2025-07-05 23:57:55 +01:00
• a4aa769c0a fix: type checking for track_rewrites key [pr] (#11104) qazalandGitHub 2025-07-05 20:11:21 +03:00
• 81781dc12b viz: renames and spacing changes to tracing (#11102) qazalandGitHub 2025-07-05 18:40:39 +03:00
• 7619bf35e7 cleanup: remove disabled TestIndexingOrdering (#11101) qazalandGitHub 2025-07-05 18:14:37 +03:00
• 4fcfaa0ef7 viz: switch to TracingKey (#11100) qazalandGitHub 2025-07-05 17:46:18 +03:00
• 458be950d9 viz: add TINY device (#11095) qazalandGitHub 2025-07-05 16:54:55 +03:00
• 4dccb2ea49 am_smi: increase kill retries (#11099) nimlgenandGitHub 2025-07-05 16:23:50 +03:00
• 39b4d72687 remove flatten and reshape in sparse_categorical_crossentropy [pr] (#11093) chenyuandGitHub 2025-07-04 15:15:27 -04:00
• 577afc9f05 hcq: remove redunt syncs and fix typing (#11096) nimlgenandGitHub 2025-07-04 21:49:47 +03:00
• 41aa54eb5a viz: resolve all graph references in python (#11087) qazalandGitHub 2025-07-04 20:35:25 +03:00
• 3d8569f6d8 hotfix: infinite loop in tracking pattern matcher (#11094) qazalandGitHub 2025-07-04 19:55:26 +03:00
• a783211fc7 viz: allow end_time=None in trace events (#11092) qazalandGitHub 2025-07-04 17:48:17 +03:00
• 17119b0f23 hip_ioctl: platform.machine added (#11084) 0xSGandGitHub 2025-07-04 19:50:24 +05:30
• 6656aa162c nv: enable huge pages (#11091) nimlgenandGitHub 2025-07-04 17:17:24 +03:00
• 01f3c4f44d memory: simpler paddr allocation logic (#11090) nimlgenandGitHub 2025-07-04 17:00:36 +03:00
• f6d55d9272 viz: pickle UPat location (#11086) qazalandGitHub 2025-07-04 13:09:00 +03:00
• 2403f126ed move printable out of UPat [pr] (#11085) qazalandGitHub 2025-07-04 12:31:11 +03:00
• 988540f401 support capturing cpu_profile on error (#11078) qazalandGitHub 2025-07-04 11:53:12 +03:00
• a2f5a54458 move sparse_categorical_crossentropy to test_ops (#11083) chenyuandGitHub 2025-07-03 21:40:54 -04:00
• 7c8ccb0267 sparse_categorical_crossentropy cleanup [pr] (#11082) chenyuandGitHub 2025-07-03 18:32:52 -04:00
• e02ee8ef1b nv: cleanups from 5090 (#11081) nimlgenandGitHub 2025-07-04 00:08:47 +03:00
• e9a01dd04a Revert "Fix division by zero in add views (#11075)" (#11080) George HotzandGitHub 2025-07-03 11:39:44 -07:00
• 19f07e72f6 Fix division by zero in add views (#11075) Sieds LyklesandGitHub 2025-07-03 20:37:59 +02:00
• 678cabc6f2 use argfix in Tensor.stack (#11077) chenyuandGitHub 2025-07-03 12:15:11 -04:00
• b695e8c4d6 viz: remove support for naming with self (#11076) qazalandGitHub 2025-07-03 17:29:14 +03:00
• 53985297bd add test, fix rewrite rule and raise error on division by zero (#11073) Sieds LyklesandGitHub 2025-07-03 14:25:06 +02:00
• 2d138c6cf1 am: factor out init_sw (#11070) nimlgenandGitHub 2025-07-03 11:01:17 +03:00
• a937ac80dc Replace ASSIGN with STORE in UPat compiler (#11065) quortusandGitHub 2025-07-03 04:15:43 +02:00
• d049639221 little setitem test (#11064) George HotzandGitHub 2025-07-02 15:10:24 -07:00
• 17d85b9793 Refactor STORE implementation in ops_python (#11060) quortusandGitHub 2025-07-02 23:29:12 +02:00
• 3b85534df0 outerworld range test [pr] (#11059) George HotzandGitHub 2025-07-02 14:28:44 -07:00
• 425d5f55c4 generate kernel dataset and upload artifact (#11063) chenyuandGitHub 2025-07-02 17:21:25 -04:00
• 09cc64eea7 remove const 0 clause in "UOp with size 0 is zero" [pr] (#11061) chenyuandGitHub 2025-07-02 16:36:40 -04:00
• 4d57437a67 add timeout to benchmark_search and mlperf action (#11058) chenyuandGitHub 2025-07-02 14:17:34 -04:00
• 6067568087 nv: remove hardcoded CTRL_CMD_VASPACE_COPY_SERVER_RESERVED_PDES (#11057) nimlgenandGitHub 2025-07-02 20:41:10 +03:00
• ad155f5454 print inputs to get_program in process replay [pr] (#11051) qazalandGitHub 2025-07-02 20:20:01 +03:00
• a22aa77c82 cleanup opts_to_apply (#11055) Ignacio SicaandGitHub 2025-07-02 14:03:19 -03:00
• a919b8325b add test_kernel_info (#11054) qazalandGitHub 2025-07-02 19:48:12 +03:00
• 3b041d188f [bounty] Singular Value Decomposition (#10875) 3 people 2025-07-02 09:06:03 -07:00
• fc42c3063e use kernel info (#11049) Ignacio SicaandGitHub 2025-07-02 12:42:32 -03:00
• e992ed10dc WebGPU on Windows (#10890) 3 people 2025-07-02 17:38:45 +02:00
• e67a6d2310 nv: tiny cleanups (#11053) nimlgenandGitHub 2025-07-02 18:37:32 +03:00
• 4626e9c172 is_numpy_ndarray helper [pr] (#11050) chenyuandGitHub 2025-07-02 09:12:53 -04:00
• 452b22c9b6 fix process replay diff in PYTHON device [pr] (#11052) qazalandGitHub 2025-07-02 11:06:46 +03:00
• 383c0bf05e notes warp_fun geohot 2025-07-01 10:36:05 -07:00
• 8ebf0abaae ONNX external_test_onnx_backend use PYTHON device for model (#10915) 3 people 2025-07-02 00:11:17 +08:00
• 8b0871ac31 viz: test for no lockup on infinite loop (#11041) qazalandGitHub 2025-07-01 17:44:20 +03:00
• fcbefde8f5 fix DiskDevice reuse (#11039) 3 people 2025-07-01 22:29:21 +08:00
• fd2c0e2626 uc warp geohot 2025-06-30 20:54:29 -07:00
• 5907f2d443 Merge branch 'master' into warp_fun George HotzandGitHub 2025-06-30 18:18:52 -07:00
• 5628e2054c hotfix: if no ranges, return None geohot 2025-06-30 18:07:56 -07:00
• fc59db0aaa Merge branch 'master' into warp_fun George HotzandGitHub 2025-06-30 15:54:57 -07:00
• 0597735f28 remove TC=3 not porting this (#11045) George HotzandGitHub 2025-06-30 15:12:49 -07:00
• cccfe6b422 hotfix: test_no_inf_loop_bottom_up geohot 2025-06-30 14:21:45 -07:00
• 752c76ceb7 tc3 shape expand [pr] (#11043) George HotzandGitHub 2025-06-30 13:38:14 -07:00
• 539b17fcbf expand local shape so shapes work [pr] (#11042) George HotzandGitHub 2025-06-30 13:03:31 -07:00