biondizzle
  • Joined on 2025-12-10
biondizzle pushed to main at biondizzle/vllm 2026-04-09 22:04:07 +00:00
e5de19ff9a [CI/Build[ Don't auto-rebase PRs with CI failures (#39443)
edee96519a [Spec Decode] fix returning size mismatch on extract hidden states proposer (#38610)
adaabb8a55 Add nightly b200 test for spec decode eagle correctness (#38577)
f7cad67412 [ASR] Fix spacing bw chunks in multi chunk audio transcription (#39116)
a8134aef4e [XPU] check is_xccl_available before oneccl warmup (#39302)
Compare 10 commits »
biondizzle created repository biondizzle/vllm 2026-04-09 21:53:58 +00:00
biondizzle pushed to master at biondizzle/m3db-vke-setup 2026-04-09 19:34:00 +00:00
f597247f56 Rename vm.vultrlabs.dev → victoriametrics.vultrlabs.dev
biondizzle pushed to master at biondizzle/m3db-vke-setup 2026-04-09 19:29:21 +00:00
bf6d62b9a8 Add VictoriaMetrics for historical metrics (Mar 13+)
biondizzle pushed to master at biondizzle/m3db-vke-setup 2026-04-09 19:00:17 +00:00
7ade5ecac8 Clean slate: 1h block sizes, remove backfill artifacts
biondizzle pushed to master at biondizzle/vllm-glm 2026-04-09 06:21:06 +00:00
139e617ed0 Clean up README with full bug analysis for ZAI
biondizzle pushed to master at biondizzle/vllm-glm 2026-04-09 05:21:00 +00:00
aa4f667ab8 Add hf.py patch to force string content format for GLM models
biondizzle pushed to master at biondizzle/vllm-glm 2026-04-09 04:28:26 +00:00
8d5da5750d patch parser
biondizzle created branch master in biondizzle/vllm-glm 2026-04-08 18:27:34 +00:00
biondizzle pushed to master at biondizzle/vllm-glm 2026-04-08 18:27:34 +00:00
40159e865e init commit
bf66b8708c GLM-5.1 tool parser with incremental streaming support
biondizzle created repository biondizzle/vllm-glm 2026-04-08 18:27:10 +00:00
biondizzle pushed to cuda-malloc-managed at biondizzle/grace-gpu-containers 2026-04-07 21:32:20 +00:00
7c79fb4ee7 fix: Update cudaMemAdvise for CUDA 13 API
biondizzle created branch cuda-malloc-managed in biondizzle/grace-gpu-containers 2026-04-07 21:20:08 +00:00
biondizzle pushed to cuda-malloc-managed at biondizzle/grace-gpu-containers 2026-04-07 21:20:08 +00:00
2757bffcb6 Add cudaMallocManaged allocator for GH200 EGM support
biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-06 17:25:07 +00:00
edf12f7996 Clean up: remove PLAN-triton-kernels.md (merged into main)
biondizzle deleted branch feature/triton-kernels from biondizzle/grace-gpu-containers 2026-04-06 17:20:06 +00:00
biondizzle pushed to main at biondizzle/grace-gpu-containers 2026-04-06 17:19:51 +00:00
e6cc28a942 Add triton_kernels for MoE support (vLLM v0.19.0)
biondizzle created branch feature/triton-kernels in biondizzle/grace-gpu-containers 2026-04-06 16:40:21 +00:00
biondizzle pushed to feature/triton-kernels at biondizzle/grace-gpu-containers 2026-04-06 16:40:21 +00:00
e6cc28a942 Add triton_kernels for MoE support (vLLM v0.19.0)
biondizzle pushed tag v0.19.0 to biondizzle/grace-gpu-containers 2026-04-06 15:02:02 +00:00