mirror of
https://github.com/deepseek-ai/DeepInfer.git
synced 2026-10-29 23:37:28 +08:00
88e70d1975
The open-source engine has no KV reuse across requests, so every turn of a
multi-turn conversation prefills its whole prompt. This adds deepinfer/hicache:
- Pinned host pools organized in pages (one page = one 128-token KV block)
plus slots for the SWA state that the production KV store persists
(select_state_slice_to_store / load_state_from_store_to_prefill_cache).
Pages are indexed by a hash chain over the prompt, LRU evicted, written
through at the end of every prefill (engine hook pe_do_save_kvcache).
- Transfers use one small CUDA kernel copying pages between GPU and pinned
host memory through UVA pointers on the engine stream ("kernel" I/O
method, ~180 GiB/s on GB300); completion is tracked with CUDA events.
- A hit is capped so that at least yoco keep_tokens remain to recompute
(bounded replay rebuilds the decoder SWA state from that suffix), then
snapped to the nearest 128-aligned position with a stored state; states
are stored at the last few boundaries of a prompt so short follow-ups hit.
The sequence is pre-allocated, filled from host and scheduled with
num_cached_tokens set (HostPrefixCache.try_resume).
- Engine: read-only Sequence.block_table binding (to copy a finished
prefill's blocks out) and its stub.
Validated on 4x GB300 with DeepSeek-V4.1-Flash through an OpenAI-compatible
server (separate PR): greedy outputs byte-identical with and without the
cache over 8 multi-turn requests; InferenceX AgentX replay at concurrency 1
served 224 requests per hour vs 99, TTFT p50 0.59 s vs 8.9 s, with 89-96%
of prompt tokens served from the cache. tests/hicache/test_host_cache.py
covers the cache logic against a fake engine.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TNVW4sqoaPqbNtSrgpA2zK
|
||
|---|---|---|
| .. | ||
| __init__.pyi | ||
| cuda_utils.pyi | ||
| engine.pyi | ||
| graph_timer.pyi | ||