dungquixote42 0f411b02e2 Fix adaptive p sampler bug with string ban (#1287) ...

* adaptive p: upadte internal state only if not rewinding

* adaptive p: conditional update for speculative decoding

* adaptive p: refactor to rewind instead of update

* adaptive p fix: better comments

* fix rewind check

* add record to handle multi-token rewind

* better comment

2026-02-20 07:11:36 +01:00

..

CMakeLists.txt

Factor out delta net (#1286)

2026-02-18 17:16:17 +01:00

llama-arch.cpp

WIP: Qwen3Next (#1266)

2026-02-16 06:50:28 +01:00

llama-arch.h

WIP: Qwen3Next (#1266)

2026-02-16 06:50:28 +01:00

llama-build-context.cpp

Factor out delta net (#1286)

2026-02-18 17:16:17 +01:00

llama-build-context.h

Factor out delta net (#1286)

2026-02-18 17:16:17 +01:00

llama-context.h

WIP: Qwen3Next (#1266)

2026-02-16 06:50:28 +01:00

llama-cparams.h

Additional graph reduce types for split mode graph (#1154)

2026-01-18 08:02:49 +02:00

llama-delta-net.cpp

Factor out delta net (#1286)

2026-02-18 17:16:17 +01:00

llama-delta-net.h

Factor out delta net (#1286)

2026-02-18 17:16:17 +01:00

llama-grammar.cpp

llama : add token matching support to llama-grammar (#1220)

2026-02-03 07:57:17 +02:00

llama-grammar.h

llama : add token matching support to llama-grammar (#1220)

2026-02-03 07:57:17 +02:00

llama-hparams.cpp

WIP: Qwen3Next (#1266)

2026-02-16 06:50:28 +01:00

llama-hparams.h

WIP: Qwen3Next (#1266)

2026-02-16 06:50:28 +01:00

llama-impl.h

server: stop processing the prompt when client disconnects (#1134)

2026-01-13 07:56:59 +02:00

llama-load-tensors.cpp

Factor out delta net (#1286)

2026-02-18 17:16:17 +01:00

llama-mmap.cpp

Enable CUDA graphs for MoE models + GPT-OSS support (#689)

2025-08-15 09:18:07 +03:00

llama-mmap.h

Enable CUDA graphs for MoE models + GPT-OSS support (#689)

2025-08-15 09:18:07 +03:00

llama-model-loader.cpp

Be able to read uint32_t and bool arrays from GGUFs (#1252)

2026-02-07 19:20:15 +02:00

llama-model-loader.h

Merge ffn_up and ffn_gate experts tensors (#1137)

2026-01-12 18:30:53 +02:00

llama-model.cpp

WIP: Qwen3Next (#1266)

2026-02-16 06:50:28 +01:00

llama-model.h

More Qwen3-Next optimizations (#1277)

2026-02-17 16:03:51 +01:00

llama-quantize.cpp

Fix very low bpw missing imatrix check (#1284)

2026-02-19 08:15:26 +01:00

llama-sampling.cpp

Fix adaptive p sampler bug with string ban (#1287)

2026-02-20 07:11:36 +01:00

llama-sampling.h

Fix adaptive p sampler bug with string ban (#1287)

2026-02-20 07:11:36 +01:00

llama-vocab.cpp

spec : add self speculative decoding, ngram and refactor (#1261)

2026-02-13 19:04:55 +01:00

llama-vocab.h

Update mtmd to improve accuracy of M-RoPE (#993)

2025-11-29 07:27:15 +01:00

llama.cpp

Fix adaptive p sampler bug with string ban (#1287)

2026-02-20 07:11:36 +01:00

unicode-data.cpp

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

unicode-data.h

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

unicode.cpp

Server: refactor and rename functions (#1151)

2026-01-18 08:16:57 +02:00

unicode.h

Enable CUDA graphs for MoE models + GPT-OSS support (#689)

2025-08-15 09:18:07 +03:00