diff --git a/src/llama-context.cpp b/src/llama-context.cpp index 82a7ef9a8466..ba0a26639c80 100644 --- a/src/llama-context.cpp +++ b/src/llama-context.cpp @@ -4153,7 +4153,7 @@ llama_context * llama_init_from_model( // exit code (measured on Qwen3-0.6B at gpu-kernels b0ed206, 2026-11-13). Refuse here instead, where the // message can name the fix. Gated on the device so every other backend keeps its q4_0 V support. // EXPIRY: remove this whole block when the READ path accepts a q4_0 V -- not when the writer lands. gpu-kernels#75 - // adds `set_rows_q4_0`, and the FA matchers still require value->type == GGML_TYPE_F16 + // merged `set_rows_q4_0`, and the FA matchers still require value->type == GGML_TYPE_F16 // (dispatch-flash-attention.cpp:238), so a run after #75 fails one node later, at attention, which is the same // graph-failure-with-no-output shape this refusal exists to prevent. Two halves, two conditions. if (params.type_v == GGML_TYPE_Q4_0) { @@ -4164,8 +4164,9 @@ llama_context * llama_init_from_model( on_hrx = name != nullptr && std::strncmp(name, "HRX", 3) == 0; } if (on_hrx) { - LLAMA_LOG_ERROR("%s: the HRX backend cannot write a q4_0 V cache (no SET_ROWS writer: gpu-kernels#75, " - "engine#679); use -ctv q8_0 or f16\n", __func__); + LLAMA_LOG_ERROR("%s: the HRX backend cannot READ a q4_0 V cache (attention requires f16 for V; " + "gpu-kernels#75 merged the SET_ROWS WRITER, the reader is still absent, engine#679); " + "use -ctv q8_0 or f16\n", __func__); return nullptr; } }