ik_llama_opt/src/graphs
Joel Farthing e21eed5f58
deepseek4: compacted sliding-window KV cache (--swa-compress) (#2266)
Co-authored-by: Joel Farthing <262452229+joelfarthing@users.noreply.github.com>
2026-08-07 08:36:08 +03:00
..
build_arctic.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_baichuan.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_bailingmoe2.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_bert.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_bitnet.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_bloom.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_chatglm.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_codeshell.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_cohere2.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_cohere2_moe.cpp Optimize Cohere2-MoE graph parallel (#1948) 2026-06-11 07:26:42 +02:00
build_command_r.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_dbrx.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_deci.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_deepseek2.cpp Apply helper functions to the MTP graph (#2238) 2026-08-03 19:27:19 +03:00
build_deepseek4.cpp deepseek4: compacted sliding-window KV cache (--swa-compress) (#2266) 2026-08-07 08:36:08 +03:00
build_dflash.cpp openpangu: opt-in compacted sliding-window KV cache (--swa-compress) (#2253) 2026-08-05 18:00:32 +03:00
build_dots1.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_ernie45.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_falcon.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_gemma.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_gemma2.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_gemma3.cpp Chores : tidy up more typos project wide (ggml directory excluded), new -ptcall alias (#2237) 2026-08-03 08:01:18 +03:00
build_gemma4.cpp Apply helper functions to the MTP graph (#2238) 2026-08-03 19:27:19 +03:00
build_glm4.cpp Apply helper functions to the MTP graph (#2238) 2026-08-03 19:27:19 +03:00
build_gpt2.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_gptneox.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_grok.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_hunyuan.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_internlm2.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_jais.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_laguna.cpp DFlash: add Laguna XS 2.1 support (#2124) 2026-07-27 07:40:10 +03:00
build_llama.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_mamba.cpp Chores : tidy up more typos project wide (ggml directory excluded), new -ptcall alias (#2237) 2026-08-03 08:01:18 +03:00
build_mellum.cpp Split mode graph for Mellum (#1920) 2026-06-04 15:20:41 +02:00
build_mimo2.cpp DFlash: support MiMo-V2.5-Pro draft conversion and runtime (#2048) 2026-06-29 13:26:29 +02:00
build_minicpm.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_minimaxm2.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_minimaxm3.cpp Fix Minimax M3 crash when -muge merges up/gate experts 2026-06-15 15:00:32 +02:00
build_mistral3.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_mpt.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_olmo.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_openai.cpp Split mode graph for MiniMax-M3 2026-06-15 08:41:34 +00:00
build_openelm.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_openpangu.cpp deepseek4: compacted sliding-window KV cache (--swa-compress) (#2266) 2026-08-07 08:36:08 +03:00
build_orion.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_phi2.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_phi3.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_plamo.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_qwen.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_qwen2.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_qwen3.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_qwen3next.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_qwen35.cpp Apply helper functions to the MTP graph (#2238) 2026-08-03 19:27:19 +03:00
build_refact.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_seedoss.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_smollm3.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_stablelm.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_starcoder.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_starcoder2.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_step35.cpp speculative : add Step 3.7 MTP support (#2250) 2026-08-07 07:23:21 +03:00
build_t5.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00
build_xverse.cpp Add extra nodes when dealing with MLA and amb (#1899) 2026-05-29 15:17:24 +03:00