Open
Description
Name and Version
Llama.cpp (build: 5415 (6a2bc8b) with MSVC 19.29.30159.0 for Windows AMD64)
Operating systems
Windows
GGML backends
CUDA
Hardware
ryzen 3600/gt 1030
Models
any model
Problem description & steps to reproduce
i've noticed that reported seed seems to be always the same: 4294967295. Ironically, it's even in the documentation for the server in the example response.. :) in the request seed field is absent.
I did test with several models in my ui but didn't do deep check in the console. however, i decided to drop a note here, because it seems to be a real case and a pretty funny bug if it's true.
First Bad Commit
No response
Relevant log output
data stream, to_send: data: {"index":0,"content":"","tokens":[],"id_slot":0,"stop":true,"model":"W:\\granite-3.3-8b-instruct-Q6_K.gguf","tokens_predicted":231,"tokens_evaluated":478,"generation_settings":{"n_predict":-1,"seed":4294967295,"temperature":2.0,"dynatemp_range":0.0,"dynatemp_exponent":1.0,"top_k":40,"top_p":0.949999988079071,"min_p":0.05000000074505806,"top_n_sigma":-1.0,"xtc_probability":0.0,"xtc_threshold":0.10000000149011612,"typical_p":1.0,"repeat_last_n":64,"repeat_penalty":1.0,"presence_penalty":0.0,"frequency_penalty":0.0,"dry_multiplier":0.0,"dry_base":1.75,"dry_allowed_length":2,"dry_penalty_last_n":8000,"dry_sequence_breakers":["\n",":","\"","*"],"mirostat":0,"mirostat_tau":5.0,"mirostat_eta":0.10000000149011612,"stop":[],"max_tokens":-1,"n_keep":0,"n_discard":0,"ignore_eos":false,"stream":true,"logit_bias":[],"n_probs":14,"min_keep":0,"grammar":"","grammar_lazy":false,"grammar_triggers":[],"preserved_tokens":[],"chat_format":"Content-only","samplers":["penalties","dry","top_n_sigma","top_k","typ_p","top_p","min_p","xtc","temperature"],"speculative.n_max":16,"speculative.n_min":0,"speculative.p_min":0.75,"timings_per_token":false,"post_sampling_probs":false,"lora":[]}, ...