Ilker Manap d6f8f433f4 CHANGELOG: one list

2026-10-30 10:39:30 +01:00

..

cpuspeed_test.go

How fast a model would answer on the cards, as this cluster would lay it out

2026-10-28 00:19:36 +01:00

cpuspeed.go

How fast a model would answer on the cards, as this cluster would lay it out

2026-10-28 00:19:36 +01:00

fit_test.go

A plan for a big model: experts spread, any number of nodes, memory said

2026-10-20 08:45:33 +02:00

fit.go

A served model can be moved to more cards, or fewer

2026-10-29 16:40:49 +01:00

gpuspeed_test.go

The explorer's card figures: MIG, NVLink, GH200, FP8 and FP4

2026-10-29 08:38:38 +01:00

gpuspeed.go

The explorer's card figures: MIG, NVLink, GH200, FP8 and FP4

2026-10-29 08:38:38 +01:00

huggingface_test.go

A plan for a big model: experts spread, any number of nodes, memory said

2026-10-20 08:45:33 +02:00

huggingface.go

A plan for a big model: experts spread, any number of nodes, memory said

2026-10-20 08:45:33 +02:00

mig_test.go

MIG: a card in MIG mode is placed as its instances, each a GPU of class <card>-mig-<profile>

2026-10-05 00:01:14 +02:00

options_test.go

A plan for a big model: experts spread, any number of nodes, memory said

2026-10-20 08:45:33 +02:00

options.go

CHANGELOG: one list

2026-10-30 10:39:30 +01:00

size_test.go

Work out whether a model fits the cluster, and how to split it

2026-09-17 07:46:53 +02:00

size.go

A plan for a big model: experts spread, any number of nodes, memory said

2026-10-20 08:45:33 +02:00

strata_test.go

CHANGELOG: one list

2026-10-30 10:39:30 +01:00

strata.go

CHANGELOG: one list

2026-10-30 10:39:30 +01:00