igneum-network/igneum
1
0
Fork 0
Code Issues Pull requests Releases Activity

plan: the 12 GB floor's cause (the shipped sp1-gpu-server refuses cards under 24 GB and allocates every prover at Setup; the prover-floor agent's source read)

Browse source 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
igneum-labs 2026-10-05 22:00:37 +00:00
parent 3f81901155
commit 23ab08202f
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/plans/proving-v1.md
View file

@ -125,7 +125,7 @@ The GPU server of SP1 6.8.1 sets the memory, not the shard: a floor of 13.9 GB f
| 32 GB (RTX 5090) | the prototype shard, 28.3 GB, 10.8 s; the v1 shard 20.4 GB, 4.3 s | the prototype shard 30.1 GB, 33 s; the v1 shard 22.2 GB, 13.2 s | on, mine and prove, today |
| 24 GB (RTX 4090, 3090) | the v1 shard 20.4 GB; the prototype shard does NOT fit (28.3 GB) | the v1 shard 22.2 GB measured on the 5090's allocation (2.3 GB spare on a 24 GB card; approximate for the card itself) | on, mine and prove, with the line "until the devnet's fee switch its shards are the prototype size, which needs 32 GB, so this card proves from the switch on" |
| 16 GB (RTX 5080, 4080) | an empty shard only (13.9 GB) | nothing (15.7 GB for an empty shard, no room for the display) | off, with the line |
| 12 GB (RTX 3060, 4070) | nothing: the floor is 13.9 GB | nothing | off; the project lead's "make sure we can prove on 12 GB cards" is OPEN: it needs a prover build with a smaller floor (an SP1 release or a fork of its GPU server), measured on a 12 GB card; the curve above is the evidence for that ask (D2) |
| 12 GB (RTX 3060, 4070) | nothing: the floor is 13.9 GB, and the shipped server refuses the card outright | nothing | off; the project lead's "make sure we can prove on 12 GB cards" is OPEN and in work: the prover-floor agent (branch prover-floor, 5 October night) read SP1 v6.8.1's GPU server source (`sp1-gpu/crates/prover_components/src/builder.rs` lines 35 to 39): it reads the card's memory, adds 4 and panics under 24 ("Unsupported GPU memory ... must be at least 24GB"), and builds its core (ELEMENT_THRESHOLD 2^28 + 2^27 elements + 2^21), recursion (2^27), shrink (2^25) and wrap (85 M element) provers at Setup whatever the mode, which is the 13.9 GB floor; no knob reaches them, so the fix is a server rebuilt from source on PC 2 (WSL2, nvcc 12.8, CUDA_ARCHS=120) with those sizes cut, measured on the same fixtures and recipe as the curve above (D2 carries the curve) |
| under 12 GB | nothing | nothing | off, mine only |
| AMD-only and Apple machines | nothing on the GPU: no zkVM proves on an AMD GPU today (`docs/analysis/amd-proving.md`, branch amd-prove); the CPU prover is about 5 minutes a shard at a 30 GB RSS whatever the shard size (PC 1, bench-log "the SP1 CPU prover on PC 1") | | off, "mines and does not prove"; the only non-NVIDIA path with a shipped backend is RISC Zero's Metal prover behind the `ProofSystem` seam (a second guest and pinned id, a verifier for both formats, no shared aggregation): an open item, not 0.3.11 |