Skip to content

llama : fix fattn reserve call n_seqs parameter #15699

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 31, 2025
+7 −6
Merged

llama : fix fattn reserve call n_seqs parameter #15699

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 7 additions & 6 deletions src/llama-context.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -281,9 +281,15 @@ llama_context::llama_context(
}

cross.v_embd.clear();

const uint32_t n_seqs = cparams.kv_unified ? 1 : cparams.n_seq_max;
const uint32_t n_tokens = std::min(cparams.n_ctx, cparams.n_ubatch);

LLAMA_LOG_DEBUG("%s: worst-case: n_tokens = %d, n_seqs = %d, n_outputs = %d\n", __func__, n_tokens, n_seqs, n_outputs);

// resolve automatic Flash Attention use
if (params.flash_attn_type == LLAMA_FLASH_ATTN_TYPE_AUTO) {
auto * gf = graph_reserve(1, 1, 0, mctx.get(), true);
auto * gf = graph_reserve(1, n_seqs, n_outputs, mctx.get(), true);
if (!gf) {
throw std::runtime_error("failed to split graph for Flash Attention check");
}
Expand Down Expand Up @@ -324,11 +330,6 @@ llama_context::llama_context(
}

// reserve worst-case graph
const uint32_t n_seqs = cparams.kv_unified ? 1 : cparams.n_seq_max;
const uint32_t n_tokens = std::min(cparams.n_ctx, cparams.n_ubatch);

LLAMA_LOG_DEBUG("%s: worst-case: n_tokens = %d, n_seqs = %d, n_outputs = %d\n", __func__, n_tokens, n_seqs, n_outputs);

int n_splits_pp = -1;
int n_nodes_pp = -1;

Expand Down
Loading