biondizzle

0 Followers · 0 Following

• Joined on 2025-12-10

Repositories

25

Projects Packages Public Activity Starred Repositories

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 13:15:58 +00:00

643d5589a3 Switch flashinfer to v0.6.6 for vLLM v0.19.0 (v0.6.7 works with v0.18.2rc0)

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 11:55:17 +00:00

3290adb0ac Upgrade vLLM to v0.19.0 for Gemma 4 support (requires transformers>=5.5.0)

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 11:40:52 +00:00

cd5d58a6f9 Patch vLLM torch_utils.py: remove hoist=True for NGC PyTorch 2.11 compatibility

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 11:08:30 +00:00

659c79638c ✅ WORKING BUILD #43 - GH200 vLLM container builds successfully

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 10:57:43 +00:00

2442906d95 Add -y flag to pip uninstall pynvml for non-interactive Docker build

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 10:52:22 +00:00

5280a28205 Bump flashinfer from v0.6.6 to v0.6.7 (required by vLLM v0.18.2rc0)

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 09:19:02 +00:00

dbca81bba2 Switch vLLM from main to v0.18.2rc0 for CUDA 13.2 compatibility

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 09:06:43 +00:00

202b9c4e23 Add -y flag to pip uninstall infinistore for non-interactive Docker build

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 09:00:20 +00:00

c2cebcf962 Add apache-tvm-ffi dependency for flashinfer build

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 08:54:46 +00:00

beb26d3573 Fix python -m build flag: use --no-isolation instead of --no-build-isolation

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 08:52:45 +00:00

4e8a765c72 Fix wheel install conflict, use python -m build instead of pip build

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 08:46:44 +00:00

ce55e45db2 Fix NGC PyTorch image tag format (26.03-py3)

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 08:44:37 +00:00

c92c4ec68a Switch to NVIDIA NGC PyTorch 26.03 base image (PyTorch 2.11.0a0, CUDA 13.2.0, ARM SBSA support)

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 08:39:37 +00:00

54e609b2c5 Update lmcache/Dockerfile to CUDA 13.0.1, PyTorch nightly, LMCache dev branch

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 08:36:38 +00:00

4980d9e49a Use PyTorch nightly with CUDA 13.0 (torch 2.11.0.dev)

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 08:31:59 +00:00

6a97539682 Fix duplicate corrupted lines in Dockerfile

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 08:26:56 +00:00

f55789c53b Bump to CUDA 13.0.1 + PyTorch 2.9.0, add version output on git checkouts

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 08:09:06 +00:00

e514e0cd1e Revert my patches - try v0.18.2rc0

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 08:05:45 +00:00

4860bcee41 Skip LMCache CUDA extensions (NO_CUDA_EXT=1)

biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-03 07:53:43 +00:00

360b0dea58 Restore CUDA 13.0.1 + patch vLLM for cuMemcpyBatchAsync API change