 Alexander Korolev
|
d6076f1d8e
deps re-stage note: MSA cutlass pin (eb61c911) staged too; AppleDouble junk purged
|
1 bulan lalu |
|
Alexander Korolev
|
bd1dc24418
deps re-stage note: FA's own cutlass pin (nvidia/cutlass 62750a2b) now in deps-src.tar.gz; vllm staged tree 67e7e6e
|
1 bulan lalu |
|
Alexander Korolev
|
250194c1c0
r18: add PR #646 (fine-grained SWA prefix hits + decoupled GLM53 target/recurrent blocks, 5.4x KV capacity); advance bases to new tips (vllm a8c796f3 w/ #649, b12x b58f34ea w/ #315)
|
1 bulan lalu |
|
Alexander Korolev
|
15c930fa14
r18: bump jovian-judgement pins to branch tip (RoCEnante #597 + NVFP4 KV + DFlash split-KV + SM121 A16 precision); fix stale r12 pins; Dockerfile header -> versions.env is source of truth
|
1 bulan lalu |
|
Alexander Korolev
|
d31e3b0b0c
glm53 aiden: local image (prod-1.1 + instanttensor), MTP spec, 512K ctx
|
1 bulan lalu |
 kilork
|
2d17cd0356
r12 clean build: SHA-pinned PR heads (550 closed), deepgemm pre-clone, lil launch-policy diff recorded
|
1 bulan lalu |
|
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)
|
1 bulan lalu |
|
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)
|
1 bulan lalu |
|
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)
|
1 bulan lalu |
