summaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Expand)Author
2025-05-02Fix model architecture name (#366)saood06
2025-04-29Apply Qwen3 PR from llama.cpp (#355)Ben Harris
2025-04-26Add GLM-4-0414 Model Support (#344)ubergarm
2025-04-26Add support for Cohere2 (#341)Kawrakow
2025-04-25Fix LLaMA-4 attention (#342)Kawrakow
2025-04-22BitNet adjustments (#338)Kawrakow
2025-04-22Add support for bitnet2b_2501 model (#337)saood06
2025-04-11Correct L4 rms_norm (#324)Kawrakow
2025-04-10LlaMA-4 support (text only) (#321)Kawrakow
2025-04-08Guard against attempts to use MLA for non-MLA models (#320)Kawrakow
2025-04-07Add copyright notices (#317)Kawrakow
2025-04-01Additional guards for interleaved quants (#299)Kawrakow
2025-03-27Make sure tensor row size is multiple of block size also when quantizing with...Kawrakow
2025-03-23Improve DeepSeek batched processing speed (#282)Kawrakow
2025-03-23Test transparent huge pages on Linux (#278)Kawrakow
2025-03-22Add Gemma3 support (text only) (#276)Kawrakow
2025-03-21Fix bug: missing parentheses in logical expression (#275)Kawrakow
2025-03-21Specify tensor name regex for tensors to be repacked (#274)Kawrakow
2025-03-21FlashMLA-3: the best of both worlds (CPU only) (#273)Kawrakow
2025-03-21Convert models to row-interleaved quants using the quantize tool (#272)Kawrakow
2025-03-19Honor mmap setting when using tensor overrides (#270)Kawrakow
2025-03-18Make Q8_0 KV cache work with mla=2,fa on CUDA (#264)Kawrakow
2025-03-18FlashMLA-2: reduce compute buffer size (CUDA and CPU) (#260)Kawrakow
2025-03-17Prepare wk_b tensors of DeepSeek models on the fly (#259)Kawrakow
2025-03-13FlashMLA-2 (CPU): faster and smaller compute buffer size (#253)Kawrakow
2025-03-10DeepSeek imatrix stuff (#250)Kawrakow
2025-03-10Faster MoE token generation on CUDA (#248)Kawrakow
2025-03-09This works on CUDA, but (#247)Kawrakow
2025-03-08Faster FlashMLA prompt processing (#246)Kawrakow
2025-03-07Custom quantization rules with regular expressions (#244)Kawrakow
2025-03-05DeepSeek CUDA Flash Attention (#241)Kawrakow
2025-03-03Flash MLA (CPU only) (#240)Kawrakow
2025-03-02SER - Smart Expert Reduction (#239)Kawrakow
2025-03-01Reduce size of compute buffers (#237)Kawrakow
2025-02-27Option to use MLA without a transposed cache (#235)Kawrakow
2025-02-27Faster MLA on CUDA (#234)Kawrakow
2025-02-25Give the user the option to override where model weights are stored (#232)Kawrakow
2025-02-23Fused MoE ffn_up and ffn_gate (#229)Kawrakow
2025-02-20Honor attn_output specified in the command line also for low-bit quantsIwan Kawrakow
2025-02-19Q8_KV: 8-bit quantization type targeting the KV cache (#208)Kawrakow
2025-02-13MLA: allow Q8_0 K-cache for MLA (#206)Kawrakow
2025-02-13Faster MLA prompt processing (#205)Kawrakow
2025-02-11DeepSeek FA support (CPU only) (#200)Kawrakow
2025-02-10 Load all MoE experts during warmup and make warmup 1 token (#198)saood06
2025-02-09Add optional MLA (#188)Kawrakow
2025-02-07cuda: non-contiguous rms norm (#190)Kawrakow
2025-02-06Rename q4_0_r4, q8_0_r4 and iq4_xs_r4 to _r8 (#189)Kawrakow
2025-02-06IQ1_M_R4: better 1.75 bpw quants (#187)Kawrakow
2025-02-05IQ1_S_R4: better 1.5 bpw quants (#185)Kawrakow
2025-01-30Deepseek-Lite (#184)Kawrakow
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-12 22:17:12 +0000