grenade

grenade closed issue blackbeard/observer#21

2026-09-14 13:31:57 +00:00

A vesting route: when 99.5% of the supply actually arrives

grenade pushed to main at blackbeard/observer

2026-09-14 13:31:57 +00:00

2bbe8e4d5d feat: a vesting route — when 99.5% of the supply actually arrives

grenade created pull request blackbeard/miner#29

2026-09-14 13:30:42 +00:00

engine-cuda: loop-structured mining_loop kernel, opt-in via MINER_CUDA_KERNEL=loop

grenade created branch perf/loop-kernel in blackbeard/miner

2026-09-14 13:30:21 +00:00

grenade pushed to perf/loop-kernel at blackbeard/miner

2026-09-14 13:30:21 +00:00

816b1efb61 engine-cuda: loop-structured mining_loop kernel behind MINER_CUDA_KERNEL

grenade opened issue blackbeard/observer#21

2026-09-14 13:25:22 +00:00

A vesting route: when 99.5% of the supply actually arrives

grenade closed issue blackbeard/observer#17

2026-09-14 12:32:17 +00:00

A network page: the figures an analyst needs to judge ecosystem health

grenade pushed to main at blackbeard/observer

2026-09-14 12:32:17 +00:00

da7f773564 feat: how concentrated the balance is, once the treasury is set aside

grenade commented on issue blackbeard/miner#1

2026-09-14 12:28:54 +00:00

Architecture: loose coupling to origin for a performance-tuned miner

State of play (2026-09-14)

Several statements above are stale; this comment is the current reading.

The repository is public and publishes release binaries (#28, first tag v4.0.2-lair.1)…

grenade closed issue blackbeard/miner#5

2026-09-14 12:28:42 +00:00

engine-gpu: double-buffered submission so the GPU never drains between batches

grenade commented on issue blackbeard/miner#5

2026-09-14 12:28:41 +00:00

engine-gpu: double-buffered submission so the GPU never drains between batches

Closing as superseded. The bubble this was meant to hide was measured at 1.9% of batch time on the 4090 and about 5% on a 5090, and #26 recovered what was recoverable on the engine that actually…

grenade closed issue blackbeard/miner#7

2026-09-14 12:28:36 +00:00

NVIDIA WGSL kernel: port the Apple arithmetic wins without the code-size changes

grenade commented on issue blackbeard/miner#7

2026-09-14 12:28:34 +00:00

NVIDIA WGSL kernel: port the Apple arithmetic wins without the code-size changes

Closing as superseded. Every arithmetic idea listed here (carry-free wide products, the row sum folded into the multiply-add, deferred-carry accumulation, constants as immediates) has been…

grenade closed issue blackbeard/miner#8

2026-09-14 12:28:30 +00:00

CI: replace inherited workflows with a Gitea fat-binary build and deploy-on-main

grenade commented on issue blackbeard/miner#8

2026-09-14 12:28:28 +00:00

CI: replace inherited workflows with a Gitea fat-binary build and deploy-on-main

Closing: everything this issue asked for is in place and has run in anger.

Fat binary (sm_86, sm_89, sm_120 + compute_120 PTX) built with the CUDA 13.0 toolkit on the cuda-13.0 runner on…

grenade commented on issue blackbeard/observer#17

2026-09-14 12:27:39 +00:00

A network page: the figures an analyst needs to judge ecosystem health

The distribution phase, as specified, would describe the treasury

Building it now. The spec says "the share of issuance held by the top 1, 10 and 100" plus a Gini. Two measurements since this…

grenade pushed to main at blackbeard/observer

2026-09-14 11:45:44 +00:00

67e7b2ec24 fix: the waiting counter was never once visible

grenade pushed to main at blackbeard/observer

2026-09-14 11:35:55 +00:00

a245caef99 feat(ui): count the wait instead of describing it

grenade pushed to main at blackbeard/observer

2026-09-14 11:26:05 +00:00

ee575ed33f feat(ui): two columns for the stage, and a console that links out

grenade pushed to main at blackbeard/observer

2026-09-14 11:12:46 +00:00

578a54ef87 fix: the backfill was re-announcing blocks the console had already shown