furyhawk/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-07-21 02:05:35 +00:00
Code Issues Packages Projects Releases Wiki Activity
4,735 Commits 952 Branches 1 Tag

Default Branch

main

9d07d8681e · perplexity: fix int overflows in large context x vocab buffer sizing (#2150) · Updated 2026-07-18 06:13:47 +00:00
 ZIP  TAR.GZ

Branches

ik/enable_smgraph_mla_hybrid

2575143637 · Enable split mode graph for MLA models and partial offload · Updated 2026-05-19 12:34:03 +00:00    furyhawk

220
1
 ZIP  TAR.GZ
ik/mla_smgraph

7dd19e197d · Some tweaks · Updated 2026-05-18 15:52:26 +00:00    furyhawk

228
2
 ZIP  TAR.GZ
ik/gemma4_mtp_extra_output

544fc08db2 · Check for output_extra.weight when loading Gemma4 assistant models · Updated 2026-05-17 14:24:04 +00:00    furyhawk

229
1
 ZIP  TAR.GZ
ik/fix_qwen35moe_low_mtp_acceptance

d237d7b398 · Fix Gemma4 MTP · Updated 2026-05-17 14:16:10 +00:00    furyhawk

229
2
 ZIP  TAR.GZ
ik/fix_mtp_plus_muge

9b783bf22e · Fix Qwen3.5/3.6 MTP and -muge · Updated 2026-05-17 13:55:20 +00:00    furyhawk

230
1
 ZIP  TAR.GZ
ik/add_extra_output_tensor

fcbb17a8ea · Consistently use --mtp-requantize-output-tensor · Updated 2026-05-16 15:41:12 +00:00    furyhawk

231
2
 ZIP  TAR.GZ
ik/mtp_requantize_output

b5da743b3c · Handle interleaved types · Updated 2026-05-16 06:38:18 +00:00    furyhawk

233
3
 ZIP  TAR.GZ
ik/imatrix_ffn_gate

25ab82abd3 · imatrix: use data for ffn_up when data for ffn_gate is missing · Updated 2026-05-15 04:24:07 +00:00    furyhawk

237
1
 ZIP  TAR.GZ
ik/faster_imatrix

da4ebcc719 · Slightly better · Updated 2026-05-14 14:55:24 +00:00    furyhawk

239
2
 ZIP  TAR.GZ
ik/fix_ggml_nbytes

62755c24e8 · Fix ggml_nbytes · Updated 2026-05-13 14:28:06 +00:00    furyhawk

245
1
 ZIP  TAR.GZ
ik/mtp_tweaks_2

67735a4587 · More MTP tweaks · Updated 2026-05-13 09:37:26 +00:00    furyhawk

245
1
 ZIP  TAR.GZ
ik/per_step_conv_states

26591f2b57 · Cleanup · Updated 2026-05-13 05:10:41 +00:00    furyhawk

250
2
 ZIP  TAR.GZ
ik/gemma4_mtp_avoid_f32_cast

68f36e7878 · Gemma4 MTP: avoid casting KV cache to f32 · Updated 2026-05-12 11:41:48 +00:00    furyhawk

250
1
 ZIP  TAR.GZ
ik/fix_glm_mtp

1d9d2b7f1b · Fix GLM-4.5 MTP loading · Updated 2026-05-12 06:56:15 +00:00    furyhawk

250
1
 ZIP  TAR.GZ
fix-recurrent-ckpt-prealloc

7f29d4a670 · rebase branch with main · Updated 2026-05-12 01:53:33 +00:00    furyhawk

254
1
 ZIP  TAR.GZ
ik/mtp_reuse_graphs_2

16369dbf0f · MTP: Reuse graphs (again) · Updated 2026-05-11 15:31:15 +00:00    furyhawk

254
1
 ZIP  TAR.GZ
ik/avoid_per_step_ssm_copy

b28ddd49e3 · Cleanup · Updated 2026-05-11 12:22:50 +00:00    furyhawk

255
4
 ZIP  TAR.GZ
ik/avoid_recurrent_state_copy

54262626b7 · Avoid recurrent state copy · Updated 2026-05-11 09:43:22 +00:00    furyhawk

256
1
 ZIP  TAR.GZ
ik/mtp_per_step_smgraph

d81090541b · MTP: ebable per step recurrent state for split mode graph · Updated 2026-05-10 12:47:30 +00:00    furyhawk

259
1
 ZIP  TAR.GZ
ik/fix_mistral3_smgraph

e7f8d7cdbd · Fix Mistral3 split mode graph · Updated 2026-05-10 05:46:40 +00:00    furyhawk

259
1
 ZIP  TAR.GZ