sirhcm/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests 2 Actions 8 Activity
14,164 Commits 336 Branches 15 Tags
475ad15f2829dbd8afa53d596af01e981fcdc538
Commit Graph
450 Commits
Author SHA1 Message Date
geohot 475ad15f28 27b 935/47 2026-08-02 00:36:02 +00:00
geohot 6d526f0252 /raid/models/Qwen3.6-27B-IQ4_XS.gguf works at 704/40 2026-07-31 21:25:09 +00:00
geohot 3ae41d3f58 move the kernels 2026-07-31 04:38:59 +00:00
geohot 55ebf56c69 simplify llm core integration 2026-07-30 16:22:25 +00:00
geohot 5dbd9a3020 cleanups 2026-07-30 15:55:10 +00:00
geohot 3af1d62571 tests passing 2026-07-30 03:24:48 +00:00
geohot f0295493a8 Merge remote-tracking branch 'origin/master' into llm_262k_minimal 
# Conflicts:
#	extra/gemm/amd_flash_attention.py
#	tinygrad/codegen/__init__.py
#	tinygrad/runtime/ops_cpu.py
#	tinygrad/uop/ops.py
 2026-07-30 00:51:47 +00:00
geohot 6cd7cc0888 unused 2026-07-29 23:27:06 +00:00
chenyuandGitHub fd912b348c generic c0*x<c1 [pr] (#17291) 2026-07-29 18:45:23 -04:00
chenyuandGitHub 027907a544 fix c0*x<c1 symbolic [pr] (#17290) 
use `//` and not math.ceil
 2026-07-29 18:32:31 -04:00
geohot d79daa6acb all kernels in tinygrad uop language and fast 2026-07-29 22:30:59 +00:00
George HotzandGitHub 52c9e5a99e rename LOOP -> WEAK and STRONGLOOP -> LOOP (#17283) 2026-07-29 10:38:36 -07:00
qazalandGitHub e684fcc689 pm_reduce_collapse fix for re enabling stack for cat of same shape (codex) (#17251) 
* change

* stack cat

* remove nop

* change
 2026-07-29 14:47:28 +09:00
George HotzandGitHub 57ae1bc7a7 rename MULTI to UNSHARD (#17267) 
* rename MULTI to UNSHARD

* comment updates (glm)

* rename method to unshard
 2026-07-28 16:51:41 -07:00
chenyuandGitHub 23e9e76e8c DEFAULT_FLOAT/DEFAULT_INT ContextVar [pr] (#17265) 2026-07-28 19:08:18 -04:00
chenyuandGitHub fde3a8faff CAPTURE_PROCESS_REPLAY=0 default chaging test [PR] (#17261) 
* CAPTURE_PROCESS_REPLAY=0 default chaging test [PR]

quick patch before making default dtype context vars, which is quite annoying

* few more
 2026-07-28 17:32:35 -04:00
qazalandGitHub 05e4727feb arange stack regression test (#17250) 
* simple failing test

* commend out stack

* a little smaller

* work
 2026-07-28 20:00:22 +09:00
b1tgandGitHub bdbb1d702f fix shard axis through symbolic reshape (#17238) 
* fix shard axis through symbolic reshape

* bind
 2026-07-27 11:32:15 -04:00
chenyuandGitHub 818a892ebc flip from_py to use weak dtypes [pr] (#17229) 2026-07-27 10:07:00 -04:00
chenyuandGitHub 456b5b5060 fix python_alu inf (#17227) 2026-07-26 20:04:12 -04:00
geohot b434b17f90 cpu is 100/20 faster than llama.cpp 2026-07-26 15:44:12 +00:00
chenyuandGitHub 74c2121d99 promo (uint64, int) -> weakfloat like JAX [pr] (#17204) 2026-07-25 15:20:42 -04:00
chenyuandGitHub ee2ccb1f24 put weakint in dtypes.weaks [pr] (#17202) 
* put weakint in dtypes.weaks [pr]

* custom_add_var
 2026-07-25 14:00:34 -04:00
chenyuandGitHub 0a6125e571 Invalid is bool, put weakint in promo lattice [pr] (#17188) 2026-07-25 00:06:53 -04:00
geohot 0028dfc9eb Merge remote-tracking branch 'origin/master' into llm_262k_minimal 
# Conflicts:
#	tinygrad/llm/serve.py
 2026-07-24 05:07:46 +00:00
George HotzandGitHub 08eceb0ad9 llm: fix generated tokens in usage accounting (#17174) 2026-07-23 21:38:07 -07:00
geohot b3c31e391f Merge remote-tracking branch 'origin/master' into llm_262k_minimal 
# Conflicts:
#	tinygrad/llm/gguf.py
 2026-07-24 02:10:52 +00:00
chenyuandGitHub 1b616669d2 few more symbolic rules [pr] (#17161) 
bitcast twice can skip middle one; bool != False is self; two more where combine
 2026-07-23 18:05:32 -04:00
sirhcmandGitHub 6ee16eb1fa split out LLVM compilers (#17160) 2026-07-23 17:45:23 -04:00
chenyuandGitHub 250de4b142 use stack for same shape cat [pr] (#17156) 
same device multi cat benefits too
 2026-07-23 13:50:28 -04:00
chenyuandGitHub 9267fca91a use STACK in wino (#17155) 
STACK is great
 2026-07-23 13:02:42 -04:00
chenyuandGitHub e9a86c99ed more symmetrical x//d<c -> x<c*d [pr] (#17146) 
* more symmetrical x//d<c -> x<c*d [pr]

* parse_valid too
 2026-07-23 00:19:53 -04:00
chenyuandGitHub 6a9c23b1c1 more symmetrical div_and_mod_symbolic [pr] (#17145) 2026-07-22 23:34:03 -04:00
chenyuandGitHub 855175123b fix z3 AND in validate (#17139) 2026-07-22 16:09:28 -04:00
chenyuandGitHub a7c693d2fd rework pm_lower_weakint [pr] (#17136) 
deleted pm_no_index and many "remove hanging casts"
 2026-07-22 15:53:11 -04:00
chenyuandGitHub 557e674861 delete pm_index_invalid [pr] (#17130) 2026-07-22 11:50:08 -04:00
chenyuandGitHub 17557d7fdf bring back fold_where_closure [pr] (#17134) 
* bring back fold_where_closure [pr]

generic enough to delete delete pm_index_invalid

* cannot cache self
 2026-07-22 11:08:14 -04:00
chenyuandGitHub b1060ca708 don't promote dtype in _pad_constant [pr] (#17125) 2026-07-21 18:13:50 -04:00
chenyuandGitHub 46b82d4755 don't auto cast cond for WHERE (#17115) 
no or_casted all WHEREs with single mixin, matched torch
 2026-07-21 13:00:07 -04:00
chenyuandGitHub f64f96ec59 broadcast_axes [PR] (#17112) 
prerequisite to simplify broadcasting logic and make it implicit
 2026-07-21 11:53:12 -04:00
sirhcmandGitHub f3a5337825 correct spelling of coalesce (#17103) 2026-07-20 21:44:04 -04:00
chenyuandGitHub 13ca9bd8a6 remove dtypes.index again (#17104) 
also reverted some dtype change, the split made things needlessly complicated
 2026-07-20 20:30:04 -04:00
sirhcmandGitHub 980748ccfc add multiple_of to ParamArg (#17101) 2026-07-20 20:11:54 -04:00
geohot 317a6b0a3e llm: speed up Qwen3.6 serving 2026-07-20 21:33:13 +00:00
George HotzandGitHub f7ce7f330d llm: minor fixes + tests (#17099) 
* llm: minor fixes + tests

* error
 2026-07-20 14:31:20 -07:00
Pol Puigdemont PlanaandGitHub ef77963cfd derivative of logsumexp is independent of max (#17088) 
same as #7009 but for logsumexp and logcumsumexp.
fwd+bwd kernel count 5 -> 3 for both. gradients unchanged
(ties, -inf masks, torch-compared at grad_atol=1e-7).
 2026-07-20 06:52:16 -07:00
chenyuandGitHub 0146a30125 improve cast to unsign min_max [pr] (#17078) 2026-07-18 21:58:41 -04:00
George HotzandGitHub b53cd35cff llm: make tokenizer fast (kimi) (#17077) 
* llm: make tokenizer fast

* simpler

* re.escape + qcom mypy fix
 2026-07-18 17:31:59 -07:00
chenyuandGitHub f315df29a0 no weak Tensor from and to real buffer (#17067) 
* no weak Tensor from and to real buffer

creation, assign, safe_save

* is_numpy_ndarray to tensor

* one more
 2026-07-17 16:09:10 -04:00
George HotzandGitHub 86a6ad8ed2 llm: split cli.py into serve.py with the HTTP server (#17065) 
* llm: split cli.py into serve.py with the HTTP server

* min edit
 2026-07-17 10:45:37 -07:00