mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-05-22 19:47:49 +00:00
52fb93a2bd
The destroy() function in server_context_impl only cleaned up the main model and context (via llama_init.reset()) but did not free the speculative decoder (spec), draft context (ctx_dft), or draft model (model_dft). For MTP (Multi-Token Prediction) models, ctx_dft holds GPU-allocated resources (KV cache, compute buffers) that are not freed when entering the sleeping state. On each sleep/resume cycle, new resources are allocated without the old ones being freed, leading to a VRAM leak that eventually crashes the server with out-of-memory errors. Fix by explicitly resetting spec, ctx_dft, and model_dft in destroy() before resetting llama_init, ensuring proper cleanup order to avoid use-after-free. ref: https://github.com/ggml-org/llama.cpp/issues/23395 Assisted-by: llama.cpp:local pi |
||
|---|---|---|
| .. | ||
| batched-bench | ||
| cli | ||
| completion | ||
| cvector-generator | ||
| export-lora | ||
| fit-params | ||
| gguf-split | ||
| imatrix | ||
| llama-bench | ||
| mtmd | ||
| parser | ||
| perplexity | ||
| quantize | ||
| results | ||
| rpc | ||
| server | ||
| tokenize | ||
| tts | ||
| ui | ||
| CMakeLists.txt | ||