| .. |
|
checksums
|
97329c6b10
r27 build dir: clone-at-pin (no tarballs), gated vllm/b12x/lmcache stages, in-build deps fetch w/ pin gates
|
1 mese fa |
|
locks
|
97329c6b10
r27 build dir: clone-at-pin (no tarballs), gated vllm/b12x/lmcache stages, in-build deps fetch w/ pin gates
|
1 mese fa |
|
patches-eugr
|
97329c6b10
r27 build dir: clone-at-pin (no tarballs), gated vllm/b12x/lmcache stages, in-build deps fetch w/ pin gates
|
1 mese fa |
|
Dockerfile
|
d736662719
r27: explicit TORCH_CUDA_ARCH_LIST=12.1a in vllm-builder (stage-env loss -> sm120-only kernels)
|
1 mese fa |
|
apt-sources.list
|
97329c6b10
r27 build dir: clone-at-pin (no tarballs), gated vllm/b12x/lmcache stages, in-build deps fetch w/ pin gates
|
1 mese fa |
|
build.sh
|
97329c6b10
r27 build dir: clone-at-pin (no tarballs), gated vllm/b12x/lmcache stages, in-build deps fetch w/ pin gates
|
1 mese fa |
|
fetch-deps.sh
|
35d8f090b2
r27 fetch-deps: recursive gitlink population (FlashMLA/qutlass/FlashKDA cutlass vendors; -d stub trap fixed)
|
1 mese fa |
|
lmcache-runtime-requirements.txt
|
97329c6b10
r27 build dir: clone-at-pin (no tarballs), gated vllm/b12x/lmcache stages, in-build deps fetch w/ pin gates
|
1 mese fa |
|
patch_cuda_sm12x.py
|
97329c6b10
r27 build dir: clone-at-pin (no tarballs), gated vllm/b12x/lmcache stages, in-build deps fetch w/ pin gates
|
1 mese fa |
|
versions.env
|
97329c6b10
r27 build dir: clone-at-pin (no tarballs), gated vllm/b12x/lmcache stages, in-build deps fetch w/ pin gates
|
1 mese fa |
Alexander Korolev
d736662719
r27: explicit TORCH_CUDA_ARCH_LIST=12.1a in vllm-builder (stage-env loss -> sm120-only kernels)