 kilork
|
de62327a2b
ledger: dsv4vision tool-eval-bench c1 (81/100, tg 34.1/31.0/29.1, deployability 74, 3 safety-critical fails)
|
1 bulan lalu |
|
kilork
|
8d49ca7159
dsv4vision: env-gated openai mm branch (VLLM_DSV4_MM), worker shape-follow patches, local-NVMe weights (dgx3+dgx4), cache-clear runbook; text lane verified exact on new boots
|
1 bulan lalu |
|
kilork
|
d34e7758bc
dsv4-vision lane: text serving verified on eugr fork (34.9 tok/s, accept 0.714); OpenAI-mm processor gap documented
|
1 bulan lalu |
|
kilork
|
1617621e8c
dsv4-flash-vision lane (sfxnz day-0 plugin port) + MNBT1024 assertion result
|
1 bulan lalu |
|
kilork
|
65916245e2
lab-quant variant of 0rand winning config (forum 381350 #119): GMU 0.89, MNBT 2048, KV auto-size
|
1 bulan lalu |
|
kilork
|
5e3c35617b
EXL3 lane benched: 88/100 quality, 23.1/24.1 t/s flat, deployability 77 (best of four glm53 lanes)
|
1 bulan lalu |
|
kilork
|
e81ae9b4ec
EXL3 recipe: verified serving via instanttensor loader overlay
|
1 bulan lalu |
|
kilork
|
25f2710be9
EXL3 recipe boot diagnosis + sparkrun bench numbers in spec ledger
|
1 bulan lalu |
|
kilork
|
caae1b0ead
4p67: eager vs CUDA-graphs A/B measured (tool-eval-bench, seed 42)
|
1 bulan lalu |
 Alexander Korolev
|
96c6bfe777
feat(recipes): lab defaults to --enforce-eager — MTP+CUDA-graphs quality bug confirmed by A/B bench
|
1 bulan lalu |
|
Alexander Korolev
|
28e08afa73
feat(recipes): redhat @ 524288 ctx — pinned 10 GiB KV, autotune off, 4096 chunks, lab image for CC-12.0 topk guards
|
1 bulan lalu |
|
Alexander Korolev
|
3d30d85655
docs(specs): lab /174 explained — TC-53 excluded on 120s infra timeout (score unchanged at 89 either way)
|
1 bulan lalu |
|
Alexander Korolev
|
a0383302e3
docs(specs): redhat MTP reality check — RedHatAI ships mtp as separate -mtp-FP8 variant repos (GLM-5.2 pattern); none for 5.3-Flash yet
|
1 bulan lalu |
|
Alexander Korolev
|
5730abbfee
docs(specs): GLM-5.3-Flash three-way quant benchmark on ds4 (measured)
|
1 bulan lalu |
