happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
llama.cpp/examples/lookup
History
Daniele Pinna 1488339138
lookup, lookahead: fix crash when n_ctx not specified (#18729) 
* lookup, lookahead: fix crash when n_ctx not specified

Since PR #16653 (Dec 15, 2025), the default n_ctx is 0 to enable automatic
GPU memory fitting. This causes llama-lookup and llama-lookahead to crash
when run without explicit -c flag:

    GGML_ASSERT(batch.seq_id[batch.n_tokens] && "llama_batch size exceeded")

Root cause: Both examples use params.n_ctx directly for batch initialization,
but params.n_ctx remains 0 even after the context is properly initialized
to n_ctx_train internally.

Bug history:
- Nov 2023: lookahead.cpp created (PR #4207) with params.n_ctx pattern
- Dec 2023: lookup.cpp created (PR #4484) with same pattern
- Nov 2024: default n_ctx changed to 4096 (PR #10136) - bug dormant
- Dec 2025: default n_ctx changed to 0 (PR #16653) - bug activated

The bug was dormant for 2+ years because params.n_ctx defaulted to 512,
then 4096. PR #16653 changed it to 0 for GPU auto-fitting, triggering
the crash.

Fix: Use llama_n_ctx(ctx) to get the actual runtime context size, matching
the pattern already used elsewhere in lookup.cpp (line 72) and in
speculative.cpp/speculative-simple.cpp.

Tested: llama-lookup now works without -c flag (12.5% acceptance on
Gemma-3-1B).

Note: llama-lookahead has a separate pre-existing issue with sequence
initialization (n_seq_max=1 vs W+G+1 needed) that is unrelated to this fix.

* lookahead: fix n_seq_max and kv_unified configuration

Lookahead decoding requires:
- W + G + 1 = 31 sequences for parallel Jacobi decoding
- Unified KV cache for coupled sequences in batch splitting

These requirements were broken after PR #14482 changed validation logic.

Consolidates fix from PR #18730 per maintainer request.

Commit message drafted with Claude.
 		2026-01-30 22:10:24 +02:00
..
CMakeLists.txt ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
README.md repo : update links to new url (#11886) 2025-02-15 16:40:57 +02:00
lookup-create.cpp spec : add self‑speculative decoding (no draft model required) + refactor (#18471) 2026-01-28 19:42:42 +02:00
lookup-merge.cpp common : use common_ prefix for common library functions (#9805) 2024-10-10 22:57:42 +02:00
lookup-stats.cpp spec : add self‑speculative decoding (no draft model required) + refactor (#18471) 2026-01-28 19:42:42 +02:00
lookup.cpp lookup, lookahead: fix crash when n_ctx not specified (#18729) 2026-01-30 22:10:24 +02:00

README.md

llama.cpp/examples/lookup

Demonstration of Prompt Lookup Decoding

https://github.com/apoorvumang/prompt-lookup-decoding

The key parameters for lookup decoding are ngram_min, ngram_max and n_draft. The first two determine the size of the ngrams to search for in the prompt for a match. The latter specifies how many subsequent tokens to draft if a match is found.

More info:

https://github.com/ggml-org/llama.cpp/pull/4484 https://github.com/ggml-org/llama.cpp/issues/4226