Block a user
tacit
synced commits to refs/pull/510/merge at tacit/nanochat from mirror
2026-02-13 14:09:54 +00:00
e569b59f92
delete torchao dependency, create our own exact API-matched version of Float8Linear, document it very well. for some poorly understood reason, the performance is not only ~identical but actually runs 3% faster. despite of it being significantly simpler and much less code. i don't fully understand why/how atm
tacit
synced commits to refs/pull/447/merge at tacit/nanochat from mirror
2026-02-13 14:09:54 +00:00
e569b59f92
delete torchao dependency, create our own exact API-matched version of Float8Linear, document it very well. for some poorly understood reason, the performance is not only ~identical but actually runs 3% faster. despite of it being significantly simpler and much less code. i don't fully understand why/how atm
e569b59f92
delete torchao dependency, create our own exact API-matched version of Float8Linear, document it very well. for some poorly understood reason, the performance is not only ~identical but actually runs 3% faster. despite of it being significantly simpler and much less code. i don't fully understand why/how atm
e569b59f92
delete torchao dependency, create our own exact API-matched version of Float8Linear, document it very well. for some poorly understood reason, the performance is not only ~identical but actually runs 3% faster. despite of it being significantly simpler and much less code. i don't fully understand why/how atm
ff46300720
tune miniseries just a bit, fairly cosmetic, keep to even depths where the math works out nicely in model sizing
tacit
synced commits to refs/pull/442/merge at tacit/nanochat from mirror
2026-02-13 14:09:53 +00:00
e569b59f92
delete torchao dependency, create our own exact API-matched version of Float8Linear, document it very well. for some poorly understood reason, the performance is not only ~identical but actually runs 3% faster. despite of it being significantly simpler and much less code. i don't fully understand why/how atm
ff46300720
tune miniseries just a bit, fairly cosmetic, keep to even depths where the math works out nicely in model sizing
tacit
synced commits to refs/pull/414/merge at tacit/nanochat from mirror
2026-02-13 14:09:53 +00:00
tacit
synced commits to refs/pull/312/merge at tacit/nanochat from mirror
2026-02-13 14:09:53 +00:00
e569b59f92
delete torchao dependency, create our own exact API-matched version of Float8Linear, document it very well. for some poorly understood reason, the performance is not only ~identical but actually runs 3% faster. despite of it being significantly simpler and much less code. i don't fully understand why/how atm
ff46300720
tune miniseries just a bit, fairly cosmetic, keep to even depths where the math works out nicely in model sizing
tacit
synced commits to refs/pull/429/merge at tacit/nanochat from mirror
2026-02-13 14:09:53 +00:00
e569b59f92
delete torchao dependency, create our own exact API-matched version of Float8Linear, document it very well. for some poorly understood reason, the performance is not only ~identical but actually runs 3% faster. despite of it being significantly simpler and much less code. i don't fully understand why/how atm
e569b59f92
delete torchao dependency, create our own exact API-matched version of Float8Linear, document it very well. for some poorly understood reason, the performance is not only ~identical but actually runs 3% faster. despite of it being significantly simpler and much less code. i don't fully understand why/how atm
ff46300720
tune miniseries just a bit, fairly cosmetic, keep to even depths where the math works out nicely in model sizing
e569b59f92
delete torchao dependency, create our own exact API-matched version of Float8Linear, document it very well. for some poorly understood reason, the performance is not only ~identical but actually runs 3% faster. despite of it being significantly simpler and much less code. i don't fully understand why/how atm
ff46300720
tune miniseries just a bit, fairly cosmetic, keep to even depths where the math works out nicely in model sizing
tacit
synced commits to refs/pull/311/merge at tacit/nanochat from mirror
2026-02-13 14:09:52 +00:00
e569b59f92
delete torchao dependency, create our own exact API-matched version of Float8Linear, document it very well. for some poorly understood reason, the performance is not only ~identical but actually runs 3% faster. despite of it being significantly simpler and much less code. i don't fully understand why/how atm
ff46300720
tune miniseries just a bit, fairly cosmetic, keep to even depths where the math works out nicely in model sizing
tacit
synced and deleted reference 2026-02-13 14:09:52 +00:00
refs/tags/refs/pull/399/merge at tacit/nanochat from mirror
tacit
synced and deleted reference 2026-02-13 14:09:52 +00:00
refs/tags/refs/pull/400/merge at tacit/nanochat from mirror
tacit
synced and deleted reference 2026-02-13 14:09:52 +00:00
refs/tags/refs/pull/370/merge at tacit/nanochat from mirror
tacit
synced commits to refs/pull/204/merge at tacit/nanochat from mirror
2026-02-13 14:09:52 +00:00
tacit
synced and deleted reference 2026-02-13 14:09:52 +00:00
refs/tags/refs/pull/432/merge at tacit/nanochat from mirror
e569b59f92
delete torchao dependency, create our own exact API-matched version of Float8Linear, document it very well. for some poorly understood reason, the performance is not only ~identical but actually runs 3% faster. despite of it being significantly simpler and much less code. i don't fully understand why/how atm
tacit
synced and deleted reference 2026-02-13 14:09:52 +00:00
refs/tags/refs/pull/59/merge at tacit/nanochat from mirror