Upstream: ggml-org#28652
Draft-model speculative decoding repeatedly resets CUDA graph warmup instead of converging to replay.
Environment: Linux aarch64, NVIDIA GB10 / CUDA 13, current upstream df03399b885831b2a1603b3abb0d8c156808e363; Qwen2.5 1.5B Q4_K_M target and 0.5B Q4_K_M draft.
llama-server -m qwen2.5-1.5b-instruct-q4_k_m.gguf -ngl 99 \
-md qwen2.5-0.5b-instruct-q4_k_m.gguf -ngld 99 \
--spec-type draft-simple -v
One greedy 256-token /v1/completions request produced:
- no speculation: warmup complete
2, reset 1
- draft-simple: warmup complete
26, reset 25
The alternating speculative graph variants appear to share a cache identity while their graph hashes differ, so each variant invalidates the other's warmup/update state. No single introducing commit was established.
Upstream: ggml-org#28652
Draft-model speculative decoding repeatedly resets CUDA graph warmup instead of converging to replay.
Environment: Linux aarch64, NVIDIA GB10 / CUDA 13, current upstream
df03399b885831b2a1603b3abb0d8c156808e363; Qwen2.5 1.5B Q4_K_M target and 0.5B Q4_K_M draft.One greedy 256-token
/v1/completionsrequest produced:2, reset126, reset25The alternating speculative graph variants appear to share a cache identity while their graph hashes differ, so each variant invalidates the other's warmup/update state. No single introducing commit was established.