CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

context : round n_tokens to next multiple of n_seqs when reserving (#14140)

Browse Source 
This fixes RWKV inference which otherwise failed
when the worst case ubatch.n_seq_tokens rounded to 0.
This commit is contained in:
compilade
2025-06-12 02:56:04 -04:00
committed by GitHub
parent 2e89f76b7a
commit a20b2b05bc
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-context.cpp
View File

@@ -1332,7 +1332,7 @@ ggml_cgraph * llama_context::graph_reserve(uint32_t n_tokens, uint32_t n_seqs, u
LLAMA_LOG_DEBUG("%s: reserving a graph for ubatch with n_tokens = %4u, n_seqs = %2u, n_outputs = %4u\n", __func__, n_tokens, n_seqs, n_outputs); LLAMA_LOG_DEBUG("%s: reserving a graph for ubatch with n_tokens = %4u, n_seqs = %2u, n_outputs = %4u\n", __func__, n_tokens, n_seqs, n_outputs);
if (n_tokens % n_seqs != 0) { if (n_tokens % n_seqs != 0) {
n_tokens = (n_tokens / n_seqs) * n_seqs; n_tokens = ((n_tokens + (n_seqs - 1)) / n_seqs) * n_seqs; // round to next multiple of n_seqs
n_outputs = std::min(n_outputs, n_tokens); n_outputs = std::min(n_outputs, n_tokens);
LLAMA_LOG_DEBUG("%s: making n_tokens a multiple of n_seqs - n_tokens = %u, n_seqs = %u, n_outputs = %u\n", __func__, n_tokens, n_seqs, n_outputs); LLAMA_LOG_DEBUG("%s: making n_tokens a multiple of n_seqs - n_tokens = %u, n_seqs = %u, n_outputs = %u\n", __func__, n_tokens, n_seqs, n_outputs);