BF16 greedy decode was sensitive to inter-block scheduling when logits
were close, which broke speculative-decoding verify-vs-decode parity.
- gemv.cu: write per-K-block partials, then reduce in fixed block order
in a second kernel instead of atomicAdd across K-blocks. Scratch
buffer size is now n * ceil(k / GEMV_TILE_K); gemv_scratch_elems()
exposes this to callers, and decode_graph.rs sizes fp32_hidden/q/kv/
intermediate/vocab from it.
- paged_attention.cu: replace atomicAdd merge of warp outputs with
per-warp shared partials reduced in warp-id order for both the base
and sinks kernels.
- paged_kv_cache: new block-paged KV cache; adds a pinned-host swap pool with
a second BlockAllocator, per-sequence Location {Gpu,Cpu}, and lossless
swap_out/swap_in (block-granular D2H/H2D) for vLLM-style preemption.
bytes_per_block helper exposes per-block cost for VRAM-based sizing.
- decode_graph: CUDA-graph decode path.
- qwen3/gpt2/kv_cache: paged prefill/decode forward + related updates.
- tokenizer/bins: BPE updates, new xserv-chat CLI, bench-qwen3 tweaks.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
