kilork
|
08a930e477
r12 image: adopt eugr lab build patches (12x patch_vllm_*.py) + pre-staged build sub-deps (SRC_DIR escapes) for flaky node github; ledger: lil render reference + perf push state
|
před 1 měsícem |
kilork
|
cc41c48e03
glm53 spark recipe: full lil policy alignment (b12x linear/moe backends, k=5 MTP + moe_backend, instanttensor load, mamba-cache-mode align, INSTANTTENSOR env) + mounted pre-baked JIT caches (~/sm121-cache/glm53-jit-121f, dsv4 pattern); boot 35m -> 7m, exact-391 verified
|
před 1 měsícem |
kilork
|
5283d11ce1
clean r12 image shipped: 90/100 c1 (was 88 day-0-base), entrypoint+MAX_JOBS boot fixes, ledger
|
před 1 měsícem |
kilork
|
236ce5a7f3
spark recipe: entrypoint (clean image is ENTRYPOINT []) + MAX_JOBS=2 (JIT nvcc OOM at boot); clean r12 image serving, exact-391 verified
|
před 1 měsícem |
kilork
|
3d084c54e4
cli: proper --no-follow flag (SetTrue opt-out; the SetFalse+default combo inverted semantics and lacked the negation)
|
před 1 měsícem |
kilork
|
2d17cd0356
r12 clean build: SHA-pinned PR heads (550 closed), deepgemm pre-clone, lil launch-policy diff recorded
|
před 1 měsícem |
kilork
|
9395d6d955
r12 clean build: flashinfer-python 0.6.17 from PyPI (whl-index path dead); recipe MTP:3 comment clarified (built-in MTP head, not dspark)
|
před 1 měsícem |
kilork
|
8de6340763
clean r12 rebuild: raw-cuda base per solar pattern (r12-specific refs, torch 2.13, flashinfer 0.6.17, b12x PR-head composition); docker_image_dir fixes; bench 88/100 (69-suite)
|
před 1 měsícem |
kilork
|
ac5c6c9108
NVFP4-Spark serving on our r12 fork build: spec-config attention_backend=B12X fixes MTP draft selection; intel recipe retargeted; ledger
|
před 1 měsícem |
kilork
|
191add7784
docker-images: glm53-jovian-r12 — in-docker build of lab fork (vllm base 54f6e9826c + PR heads 550-557 merges; b12x master + PR heads 260-270 merges; day-0 arm64-cu130 base; nvrtc/headers cmake fixes); teb c1 on vavrusa lane: 88/100 (default 69-scenario set)
|
před 1 měsícem |
kilork
|
56c99b6a33
recipes: dsv4-vision-exp-vavrusa — native image_url lane (eugr nightly 20260810 + instanttensor-draft + vision-exp mods), DSpark-6, NVMe weights; verified text-exact + real-photo caption (325 img tokens)
|
před 1 měsícem |
kilork
|
344479943a
recipes: intel glm53 W4A16-AutoRound (tjstewart image, gptq_marlin, entrypoint) + lab NVFP4-Spark (mtp-5 embedded; blocked on whole-network W4A4 loader); ledger: rtx6kpro source contract for own fork build
|
před 1 měsícem |
kilork
|
de62327a2b
ledger: dsv4vision tool-eval-bench c1 (81/100, tg 34.1/31.0/29.1, deployability 74, 3 safety-critical fails)
|
před 1 měsícem |
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
|
před 1 měsícem |
kilork
|
4df980f57a
publish: preserve nested overlay dirs (patches/ still flattened; --gist refused for nested); dsv4-vision: full OpenAI MM processor trio (info/processor/dummy+updates), model embed_multimodal + embed_input_ids merge, placeholder id 129264; verified sentinel/perm math in-image
|
před 1 měsícem |
kilork
|
d34e7758bc
dsv4-vision lane: text serving verified on eugr fork (34.9 tok/s, accept 0.714); OpenAI-mm processor gap documented
|
před 1 měsícem |
kilork
|
1617621e8c
dsv4-flash-vision lane (sfxnz day-0 plugin port) + MNBT1024 assertion result
|
před 1 měsícem |
kilork
|
65916245e2
lab-quant variant of 0rand winning config (forum 381350 #119): GMU 0.89, MNBT 2048, KV auto-size
|
před 1 měsícem |
kilork
|
5e3c35617b
EXL3 lane benched: 88/100 quality, 23.1/24.1 t/s flat, deployability 77 (best of four glm53 lanes)
|
před 1 měsícem |
kilork
|
e81ae9b4ec
EXL3 recipe: verified serving via instanttensor loader overlay
|
před 1 měsícem |
kilork
|
25f2710be9
EXL3 recipe boot diagnosis + sparkrun bench numbers in spec ledger
|
před 1 měsícem |
kilork
|
0410338b05
recipe: GLM-5.3-Flash EXL3-4bpw + DFlash2 on Entrpi community image
|
před 1 měsícem |
kilork
|
78a5ba1765
recipe: community sparkrun image (aidendle94) for GLM-5.3-Flash NVFP4
|
před 1 měsícem |
kilork
|
267b9daae7
build works outside the launcher repo; bundles gain a build.sh
|
před 1 měsícem |
kilork
|
caae1b0ead
4p67: eager vs CUDA-graphs A/B measured (tool-eval-bench, seed 42)
|
před 1 měsícem |
kilork
|
5ab8a05080
restore recipes/ in-tree — recipe + docker-images must share one revision
|
před 1 měsícem |
kilork
|
ee2855da38
config errors name every searched path
|
před 1 měsícem |
kilork
|
d0d210e466
move recipe data to git.kilork.org/sm121/recipes (registry data repo)
|
před 1 měsícem |
kilork
|
848772a3e7
glm53-flash-dflash2: target-side EAGLE3 port + rigorous KV-page blocker writeup
|
před 1 měsícem |
kilork
|
2599e39186
glm53-flash-nvfp4-4p67: MXFP8-attention support patchset + boot verified on ds4
|
před 1 měsícem |