Alexander Korolev
|
5b47e80fd6
r27 dflash2 BLOCKED: C4 parent-page stride assert (tree-level, both r18+r27), root cause documented
|
1 месяц назад |
Alexander Korolev
|
b3babad4a2
r27 DFlash2 lane: r18-dflash2 clone retargeted (method dflash, k=7, tree-picked backends)
|
1 месяц назад |
Alexander Korolev
|
191c035248
r27 4x DCP4 benched: 155 (-6 vs r18), KV 7.7M @ 16GiB; r27 still trailing r18 quality
|
1 месяц назад |
Alexander Korolev
|
1e1df7eb06
r27 4x DCP4 recipe (r18-4x-dcp4 clone retargeted at the r27 engine)
|
1 месяц назад |
Alexander Korolev
|
9cfed14f41
vision-373 lane benched: 161/176 new 2x record; launcher entrypoint-image support (model='', NODE_RANK/MASTER_ADDR env)
|
1 месяц назад |
Alexander Korolev
|
9cb56de106
state doc: night 2 results (aiden 159 first canonical, r27 156), next queue
|
1 месяц назад |
Alexander Korolev
|
2d74fdaca9
aiden 2x benched (159, first canonical aiden), r27 lane 156 (-2 vs r18), reports logged
|
1 месяц назад |
Alexander Korolev
|
8ad35cba78
night part 2: aiden 2x benched (159, first canonical), r27 lane 156 (-2 vs r18), reports saved
|
1 месяц назад |
Alexander Korolev
|
e9928e3ac7
night list: prod-3.73-vision = DSV4F-Vision aiden lane (replaces blocked eugr row)
|
1 месяц назад |
Alexander Korolev
|
03edc92027
night revisit: aiden lanes + prod-3.73-vision tag queued, statuses ledgered
|
1 месяц назад |
Alexander Korolev
|
d736662719
r27: explicit TORCH_CUDA_ARCH_LIST=12.1a in vllm-builder (stage-env loss -> sm120-only kernels)
|
1 месяц назад |
Alexander Korolev
|
afd95f742d
r27 lane: glm53-flash-r27-spark (best 2x config on the r27 engine)
|
1 месяц назад |
Alexander Korolev
|
f599efe741
skill: jovian-images (clone-at-pin builds, rev adoption, GB10 deltas, pitfall ledger)
|
1 месяц назад |
Alexander Korolev
|
35d8f090b2
r27 fetch-deps: recursive gitlink population (FlashMLA/qutlass/FlashKDA cutlass vendors; -d stub trap fixed)
|
1 месяц назад |
Alexander Korolev
|
3e63d19947
state doc: image build v2 (clone-at-pin) contract
|
1 месяц назад |
Alexander Korolev
|
9118a4648b
r27: WORKDIR in builder stages (stage split dropped inherited cwd)
|
1 месяц назад |
Alexander Korolev
|
97329c6b10
r27 build dir: clone-at-pin (no tarballs), gated vllm/b12x/lmcache stages, in-build deps fetch w/ pin gates
|
1 месяц назад |
Alexander Korolev
|
0a1a5dbcc1
typo
|
1 месяц назад |
Alexander Korolev
|
b564bd561d
ops layout: 2nodes-dac = production (operator agent), ds4 = dev lane
|
1 месяц назад |
Alexander Korolev
|
ca8bb6f448
campaign extended: 2x nvfp4 KV (154), 2x Spark (158, best 2x), 4x Spark blocked (mm_mxfp8 TP4); 4x 16G pins; JIT warm-start 9min
|
1 месяц назад |
Alexander Korolev
|
fe78fec205
add nvfp4kv spark variants (2x + 4x 16G, -Spark checkpoint on r18 img)
|
1 месяц назад |
Alexander Korolev
|
c296f735a3
4x cells: KV pin 10 -> 16 GiB (NVFP4 4x has the headroom; 2x stays 10)
|
1 месяц назад |
Alexander Korolev
|
79c40c9482
add r18 2x nvfp4_ds_mla KV lane (parity with the 4x cell)
|
1 месяц назад |
Alexander Korolev
|
cc19b5f581
persist JIT caches per node (flashinfer/torchinductor/vllm mounts in all glm53 lanes)
|
1 месяц назад |
Alexander Korolev
|
14b02ac5f5
history/night-shifts/2026-09-05.md: full combined score+perf table of the r18 campaign
|
1 месяц назад |
Alexander Korolev
|
24cfdc3a76
state doc: add --perf comparison table (all 7 lanes, llama-benchy pp/tg/TTFT)
|
1 месяц назад |
Alexander Korolev
|
5d587215dd
separation complete: r18 dir carries source tarballs; state doc records r12/r18 split + r17 rebuild caveat
|
1 месяц назад |
Alexander Korolev
|
b3d61b7af0
separate r18 from r12: dedicated docker-images/glm53-jovian-r18 dir + glm53-jovian-r18 tag; r12 dir restored to r17 pins; recipes renamed to r18 lanes
|
1 месяц назад |
Alexander Korolev
|
6327352f09
untrack regenerated data/benchmarks.sqlite (gitignore)
|
1 месяц назад |
Alexander Korolev
|
fe070bebdd
night shift: r18 built + full lane matrix (DCP4 161/176 best; eugr/DFlash2/dsv4fv-eugr documented)
|
1 месяц назад |