Open source · Contribution journal
Zro ♥ open source.
A live record of the serving work we build upstream—so the systems we rely on get better for everyone.
Live GitHub data · Refreshes hourly · 19 of 19 tracked pull requests
Project
Status
Zro → AITER
Open[ASM] [HIP] Replace gfx950 f4gemm 256x256 kernel with a persistent one
Zro → vLLM
Open[ROCm][Kimi-K3] Add moonmath kernels for gfx942 MXFP4 SiTU MoE and MLA decode, with decode context parallelism
Zro → vLLM
Open[Perf][Attention] Run non-causal DFlash draft rows on the Triton 3D kernel
Zro → vLLM
Open[Bugfix][ROCm][Kimi-K3] Feed the DFlash drafter the AttnRes mixture instead of prefix sum
Zro → SGLang
Mergedfix(dsa): budget and report the indexer key cache in the KV pool sizing
Zro → SGLang
Closed[spec decoding] Support block verification for rejection sampling
Zro → SGLang
Mergedfeat(dsa): packed-ragged sparse-MLA prefill — batching + radix + chunked prefill
Zro → SGLang
Mergedfix(dsa): route skip_offset "full" layers sparse in decode + prefill (remove unconditional dense front-block)
Zro → SGLang
Open[AMD] moonmath kernels for gfx942: MLA decode, speculative verify, DCP, and MXFP4 MoE
Zro → SGLang
Open[AMD] Split-KV verify on gfx942: CU-aware split cap, bidirectional draft blocks
Zro → SGLang
Mergedfix(linear): reshard block-quant scale for jax 0.10 explicit-mesh shard_map
Zro → SGLang
Mergedfeat(dsa): fused sparse-MLA prefill for DeepSeek Sparse Attention (opt-in)
Zro → SGLang
Mergedfix(profiler): honour explicit host_tracer_level=0 / python_tracer_level=0
Zro → SGLang
Closed