firecoperana 233898704c server: enable checkpoint for recurrent models ...

create checkpoint after cancel

fix ban string and rm context during rewind

add checkpoint interval

only save recurrent cache

2026-02-25 07:46:19 -06:00

..

CMakeLists.txt

Factor out delta net (#1286)

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

llama-arch.cpp

Fix llm_arch_is_hybrid (#1305)

2026-02-23 08:55:53 +01:00

llama-arch.h

Qwen3.5-MoE: fix regenerating message error (#1295)

2026-02-21 18:24:12 +01:00

llama-build-context.cpp

server: enable checkpoint for recurrent models

2026-02-25 07:46:19 -06:00

llama-build-context.h

Graph parallel for Qwen3-Next (#1292)

2026-02-23 07:58:00 +01:00

llama-context.h

Add MTP decoding support for GLM-4.x MoE (#1270)

2026-02-22 18:14:39 +01:00

llama-cparams.h

Fused delta-net (#1315)

2026-02-25 14:12:48 +01:00

llama-delta-net.cpp

Fused delta-net (#1315)

2026-02-25 14:12:48 +01:00

llama-delta-net.h

Fused delta-net (#1315)

2026-02-25 14:12:48 +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

Add MTP decoding support for GLM-4.x MoE (#1270)

2026-02-22 18:14:39 +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

Display the size of the tensors overriden during the tensor loading (#1318)

2026-02-25 07:36:27 +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

server: enable checkpoint for recurrent models

2026-02-25 07:46:19 -06:00

llama-model.h

Fix max nodes (again) (#1306)

2026-02-23 11:17:37 +01:00

llama-quantize.cpp

Llama-quantize: Partial requant feature (#1313)

2026-02-25 07:25:15 +01:00

llama-sampling.cpp

adaptive p: collect probability before logit bias (#1314)

2026-02-24 15:39:17 +01:00

llama-sampling.h

adaptive p: collect probability before logit bias (#1314)

2026-02-24 15:39:17 +01:00

llama-vocab.cpp

Qwen3.5-MoE support (#1288)

2026-02-21 08:33:06 +01:00

llama-vocab.h

Qwen3.5-MoE support (#1288)

2026-02-21 08:33:06 +01:00

llama.cpp

server: enable checkpoint for recurrent models

2026-02-25 07:46:19 -06:00

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