1,373 commits

Author	SHA1	Message	Date
wozeparrot	a3d59faef6	llama: don't save weight (#16252)	2026-05-18 17:05:45 -07:00
qazal	18b102f355	llama: also use 7.1 comgr, update startup_walltime.sh (#16253)	2026-05-19 08:59:02 +09:00
qazal	98b8a2b407	llama: use hipcc 7.1 version (#16250)	2026-05-19 08:09:57 +09:00
chenyu	dcee90aa3f	remove requires_grad use in extra/examples (#16238) ... except the ones fed into optimizer	2026-05-16 18:40:26 -04:00
qazal	ebcb7b7cc0	fp8 gemm tests with scale args (#16231) ... * update atol * update fp8 path * more work * update profile.sh	2026-05-16 20:47:58 +09:00
wozeparrot	159694347e	llama: fix running flat_llama (#16224)	2026-05-15 20:16:48 -07:00
George Hotz	2549b14ec2	fix caformer onnx run (#16222)	2026-05-15 15:08:36 -07:00
chenyu	07a172dbbb	remove noop requires_grad_ calls (#16213)	2026-05-15 13:31:10 -04:00
chenyu	409bb0c9ad	requires_grad cannot be None (#16212) ... final goal is to remove requires_grad, first change the default to True, and don't allow None	2026-05-15 02:01:04 -04:00
wozeparrot	b4d267dfd4	llama: only save when small (#16208)	2026-05-14 17:46:29 -07:00
wozeparrot	88ac2ac1fd	llama: cleanups (#16189)	2026-05-13 17:08:06 -07:00
wozeparrot	e97f2c1114	llama: only gemm + fa custom kernel (#16180) ... * llama: tie store to grad directly * llama: set mp flags * llama: non fused grad fp8 quantize path	2026-05-12 21:03:49 -07:00
wozeparrot	e9359d9e7d	more llama mp fixes (#16151) ... * llama: SPLIT_W13 * llama: fix with no fused kernels * llama: cast to bf16 on non asm_gemm patH * llama: new mp flags	2026-05-11 21:29:23 -07:00
wozeparrot	026688f03f	llama: move to correct dir (#16118)	2026-05-08 19:42:16 -07:00
chenyu	072db9924c	div to mixin (#16078) ... also deleted idiv method	2026-05-07 12:52:37 -04:00
qazal	a9a87ad8fd	viz/cli: less flags (#16076) ... * viz/cli: merge -s and -i flags * only -t * merge parser * fix	2026-05-08 00:22:40 +09:00
wozeparrot	730fa66bf3	llama speed 6 (#16071)	2026-05-06 20:51:03 -07:00
wozeparrot	ab6218bc92	llama mp fixes (#16050)	2026-05-05 15:35:32 -07:00
wozeparrot	528d35e306	llama speed 4 (#15993)	2026-04-30 17:14:41 -07:00
wozeparrot	0080489abe	llama: use env vars (#15978)	2026-04-29 12:37:15 -07:00
wozeparrot	ef09071073	llama: speed 2 (#15960)	2026-04-28 20:44:37 -07:00
nimlgen	77965a22e5	local optimize as rewrite (#15953) ... * local optimize as rewrite * better * x * slighly rename * fix * ugh * remove * x * remove * not weak	2026-04-28 22:51:04 +03:00
wozeparrot	5e861cd2c4	llama: move llama kernels to llama_kernels (#15952)	2026-04-27 22:48:53 -07:00
nimlgen	4164666c72	programinfo (#15942) ... * programinfo * fix * m * x * x * changes * x * fix * rm	2026-04-27 23:12:03 +03:00
qazal	9a23de7d27	viz/cli: unify profile and rewrites, -s ALL default (#15931) ... * work * workg * better * cleanup * better defaults * --ls * better * work * update llama * update	2026-04-25 22:31:24 +09:00
nimlgen	768106a542	remove schedule from extra/docs/examples (#15929) ... * remove schedule from extra/docs/examples * f	2026-04-25 14:09:12 +03:00
Denys Melnyk	1fdcb13bfb	webgpu: fix weight lookup in export_model after compile_net key change (#15919) ... * fix lookup site in export_model_webgpu after refactoring webgpu (sd): fix export_model weight lookup after compile_net changes fix lookup site in export_model_webgpu after refactoring * add regression test	2026-04-25 10:04:55 +03:00
wozeparrot	4b908b6e2c	llama: fused ce loss (#15920)	2026-04-24 20:01:24 -07:00
wozeparrot	9d134a2848	llama: fix fakedata timing (#15905)	2026-04-23 21:37:03 -07:00
wozeparrot	d3cbd781d9	llama: use fused norm mul quantize for w13 (#15878)	2026-04-22 21:27:41 -07:00
George Hotz	0c3260d5d9	rename VECTORIZE to STACK (#15880)	2026-04-23 10:43:42 +08:00
wozeparrot	87378331e8	llama: fused mul quantize fp8 (#15863)	2026-04-21 20:58:37 -07:00
Christopher Milan	99a0debd62	Device.count() (#15842)	2026-04-21 16:46:38 -04:00
nimlgen	ae9b84d32f	rm beam uop (#15844)	2026-04-21 13:10:26 +03:00
qazal	f9655af2a3	viz/cli: move to tinygrad (#15835) ... * move cli * update imports * cleanup the readme * edit * work * details * python -m tinygrad.viz.cli * do not execv in non tty * option * lint * simpler * gemm pmc	2026-04-21 13:35:10 +09:00
George Hotz	67ed4c4eb3	move gguf stuff from nn/state.py to llm/gguf.py (#15783) ... * move gguf stuff from nn/state.py to llm/gguf.py * docs	2026-04-20 09:41:43 +08:00
wozeparrot	f28ea84de2	llama: fused silu fp8 amax (#15798) ... * llama: combined w13 * llama: fused swiglu+fp8 * llama: fix amax interleaving * llama: don't need seperate matmul	2026-04-19 12:03:55 +08:00
nimlgen	022d8c4a11	remove jit_cache usage in extra/examples (#15808) ... * remove jit_cache usage in extra/examples * cached	2026-04-18 23:00:18 +03:00
wozeparrot	06343092c8	llama: combined w13 (#15803)	2026-04-17 22:27:31 -07:00
qazal	a227dbece1	viz/cli: reconstruct DEBUG output (#15791) ... * work * work * ext * padding * at time * work * reorder * less flags * num_rows * feedback * pmc	2026-04-17 18:27:58 +03:00
wozeparrot	9e60e4a7e7	llama: native fp8 (#15733)	2026-04-16 22:16:05 -07:00
George Hotz	1ae6528bb6	move schedule into schedule (#15736) ... * move schedule into schedule * callify to root * sched docs	2026-04-15 11:03:25 +08:00
wozeparrot	3721c60bef	llama: bs 16 (#15737)	2026-04-14 19:52:03 -07:00
wozeparrot	480ad264a4	llama: per device amax (#15735)	2026-04-14 19:01:17 -07:00
chenyu	3394d18066	size*itemsize -> nbytes (#15729) ... and some UOp.size removal to prep for size to mixin change	2026-04-14 16:27:54 -04:00
wozeparrot	2b8d303f75	allreduce in precast dtype (#15689)	2026-04-13 20:24:12 -07:00
qazal	054d78e6ff	fix llama profile.sh NULL source (#15685)	2026-04-11 22:56:05 +09:00
wozeparrot	457508d5a0	llama: save more 2 (#15681)	2026-04-11 01:03:36 -07:00
wozeparrot	590464c8d8	llama: only support wqkv path + cleanups (#15680) ... * llama: only support wqkv path + cleanups * llama: missing transpose	2026-04-11 07:39:27 +08:00
wozeparrot	55bcd7cc9e	llama amax outside (#15670)	2026-04-09 23:08:03 -07:00