Add GitHub data: filename sanitization (#640)

Browse Source

...

This commit is contained in:

Thomas

2025-07-23 13:31:53 +02:00

committed by GitHub

parent 3600d82e98

commit eaa2510a28

626 changed files with 0 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

0

github-data/pull_requests/1-Offload Bitnet token embeddings to the GPU.md → github-data/pull_requests/1 - Offload Bitnet token embeddings to the GPU.md

0

github-data/pull_requests/10-iq4_k_ speedup quantization by a factor of ~2.md → github-data/pull_requests/10 - iq4_k_ speedup quantization by a factor of _2.md

0

github-data/pull_requests/101-Enable q6_0 in flash attention.md → github-data/pull_requests/101 - Enable q6_0 in flash attention.md

0

github-data/pull_requests/102-Add support for Granite and GraniteMoE models.md → github-data/pull_requests/102 - Add support for Granite and GraniteMoE models.md

0

github-data/pull_requests/105-Fix quantized k-cache without FA.md → github-data/pull_requests/105 - Fix quantized k-cache without FA.md

0

github-data/pull_requests/106-Bitnet changes.md → github-data/pull_requests/106 - Bitnet changes.md

0

github-data/pull_requests/107-Faster IQ1_BN Metal implementation.md → github-data/pull_requests/107 - Faster IQ1_BN Metal implementation.md

0

github-data/pull_requests/108-Another Bitnet performance improvement on Metal.md → github-data/pull_requests/108 - Another Bitnet performance improvement on Metal.md

0

github-data/pull_requests/109-Bitnet CUDA improvements.md → github-data/pull_requests/109 - Bitnet CUDA improvements.md

0

github-data/pull_requests/11-Faster iq3_k and iq5_k quantization.md → github-data/pull_requests/11 - Faster iq3_k and iq5_k quantization.md

0

github-data/pull_requests/110-Bitnet_ use the fused mul-silu in the FFN network.md → github-data/pull_requests/110 - Bitnet_ use the fused mul-silu in the FFN network.md

0

github-data/pull_requests/111-Use fused mul - unary op also for MoE models.md → github-data/pull_requests/111 - Use fused mul - unary op also for MoE models.md

0

github-data/pull_requests/112-Faster MoE inference.md → github-data/pull_requests/112 - Faster MoE inference.md

0

github-data/pull_requests/113-Trellis quantization.md → github-data/pull_requests/113 - Trellis quantization.md

0

github-data/pull_requests/114-MMQ Kernel for Q6_0 (pretty please!).md → github-data/pull_requests/114 - MMQ Kernel for Q6_0 _pretty please_.md

0

github-data/pull_requests/115-MMQ for Q6_0.md → github-data/pull_requests/115 - MMQ for Q6_0.md

0

github-data/pull_requests/116-Use Q6_0 instead of Q5_1 for tensors incompatible with IQ5_K_Q5_K.md → github-data/pull_requests/116 - Use Q6_0 instead of Q5_1 for tensors incompatible with IQ5_K_Q5_K.md

0

github-data/pull_requests/117-Some minor quant strategies tweaks.md → github-data/pull_requests/117 - Some minor quant strategies tweaks.md

0

github-data/pull_requests/118-IQ4_NL_X4.md → github-data/pull_requests/118 - IQ4_NL_X4.md

0

github-data/pull_requests/119-Q4_0_R4.md → github-data/pull_requests/119 - Q4_0_R4.md

0

github-data/pull_requests/12-q2_K_ allow it to detect ternary nets and quantize accordingly.md → github-data/pull_requests/12 - q2_K_ allow it to detect ternary nets and quantize accordingly.md

0

github-data/pull_requests/120-Q8_0_R4.md → github-data/pull_requests/120 - Q8_0_R4.md

0

github-data/pull_requests/121-Q5_0_R4.md → github-data/pull_requests/121 - Q5_0_R4.md

0

github-data/pull_requests/122-Q6_0_R4.md → github-data/pull_requests/122 - Q6_0_R4.md

0

github-data/pull_requests/123-IQ4_XS_R4.md → github-data/pull_requests/123 - IQ4_XS_R4.md

0

github-data/pull_requests/124-iq2_bn_r4_ fastest Bitnet CPU implementation on the planet.md → github-data/pull_requests/124 - iq2_bn_r4_ fastest Bitnet CPU implementation on the planet.md

0

github-data/pull_requests/125-R4 improvements on ARM_NEON.md → github-data/pull_requests/125 - R4 improvements on ARM_NEON.md

0

github-data/pull_requests/126-Rename iq4_nl_x4 to iq4_nl_r4.md → github-data/pull_requests/126 - Rename iq4_nl_x4 to iq4_nl_r4.md

0

github-data/pull_requests/127-Q4_0_R4 on CUDA.md → github-data/pull_requests/127 - Q4_0_R4 on CUDA.md

0

github-data/pull_requests/128-Faster IQ4_XS_R4 on Zen4.md → github-data/pull_requests/128 - Faster IQ4_XS_R4 on Zen4.md

0

github-data/pull_requests/129-Q4_K_R4.md → github-data/pull_requests/129 - Q4_K_R4.md

0

github-data/pull_requests/13-Adding IQ2_TN for use with ternary models.md → github-data/pull_requests/13 - Adding IQ2_TN for use with ternary models.md

0

github-data/pull_requests/130-Q6_K_R4.md → github-data/pull_requests/130 - Q6_K_R4.md

0

github-data/pull_requests/131-Slightly faster Q4_K_R4 and IQ4_XS_R4 on Zen4.md → github-data/pull_requests/131 - Slightly faster Q4_K_R4 and IQ4_XS_R4 on Zen4.md

0

github-data/pull_requests/132-Q5_K_R4.md → github-data/pull_requests/132 - Q5_K_R4.md

0

github-data/pull_requests/134-Q3_K_R4.md → github-data/pull_requests/134 - Q3_K_R4.md

0

github-data/pull_requests/135-Better ARM_NEON implementation for R4 quants.md → github-data/pull_requests/135 - Better ARM_NEON implementation for R4 quants.md

0

github-data/pull_requests/136-Q2_K_R4.md → github-data/pull_requests/136 - Q2_K_R4.md

0

github-data/pull_requests/137-Fix AVX2 implementation of iq4_nl_r4.md → github-data/pull_requests/137 - Fix AVX2 implementation of iq4_nl_r4.md

0

github-data/pull_requests/138-IQ4_K_R4.md → github-data/pull_requests/138 - IQ4_K_R4.md

0

github-data/pull_requests/139-Faster R4 quants on Zen4.md → github-data/pull_requests/139 - Faster R4 quants on Zen4.md

0

github-data/pull_requests/14-Adding IQ6_K.md → github-data/pull_requests/14 - Adding IQ6_K.md

0

github-data/pull_requests/141-Q8_K_R8_ Fastest quantized matrix multiplications.md → github-data/pull_requests/141 - Q8_K_R8_ Fastest quantized matrix multiplications.md

0

github-data/pull_requests/142-BF16_R16 - 16 interleaved bf16 rows .md → github-data/pull_requests/142 - BF16_R16 - 16 interleaved bf16 rows.md

0

github-data/pull_requests/143-Slightly faster IQ4_XS_R4 on AVX2.md → github-data/pull_requests/143 - Slightly faster IQ4_XS_R4 on AVX2.md

0

github-data/pull_requests/144-Slightly faster IQ4_K_R4 on AVX2_Zen4.md → github-data/pull_requests/144 - Slightly faster IQ4_K_R4 on AVX2_Zen4.md

0

github-data/pull_requests/145-IQ3_K_R4.md → github-data/pull_requests/145 - IQ3_K_R4.md

0

github-data/pull_requests/146-IQ2_K_R4.md → github-data/pull_requests/146 - IQ2_K_R4.md

0

github-data/pull_requests/147-Be able to repack tensors at run time.md → github-data/pull_requests/147 - Be able to repack tensors at run time.md

0

github-data/pull_requests/148-Slightly better matrix x vector on Zen4_AVX2 for iq2_k_r4, iq3_k_r4, iq4_k_r4.md → github-data/pull_requests/148 - Slightly better matrix x vector on Zen4_AVX2 for iq2_k_r4_ iq3_k_r4_ iq.md

0

github-data/pull_requests/149-IQ5_K_R4.md → github-data/pull_requests/149 - IQ5_K_R4.md

0

github-data/pull_requests/150-IQ4_KS_R4.md → github-data/pull_requests/150 - IQ4_KS_R4.md

0

github-data/pull_requests/151-fix typo.md → github-data/pull_requests/151 - fix typo.md

0

github-data/pull_requests/152-IQ3_XXS_R4.md → github-data/pull_requests/152 - IQ3_XXS_R4.md

0

github-data/pull_requests/153-IQ3_XXS_R4.md → github-data/pull_requests/153 - IQ3_XXS_R4.md

0

github-data/pull_requests/154-IQ2_XXS_R4.md → github-data/pull_requests/154 - IQ2_XXS_R4.md

0

github-data/pull_requests/155-IQ2_XS_R4.md → github-data/pull_requests/155 - IQ2_XS_R4.md

0

github-data/pull_requests/156-IQ2_S_R4.md → github-data/pull_requests/156 - IQ2_S_R4.md

0

github-data/pull_requests/157-R4 i-quants improvements.md → github-data/pull_requests/157 - R4 i-quants improvements.md

0

github-data/pull_requests/158-Faster R4 legacy quants.md → github-data/pull_requests/158 - Faster R4 legacy quants.md

0

github-data/pull_requests/16-Fix Makefile.md → github-data/pull_requests/16 - Fix Makefile.md

0

github-data/pull_requests/161-MSVC fixes.md → github-data/pull_requests/161 - MSVC fixes.md

0

github-data/pull_requests/162-IQ3_S_R4.md → github-data/pull_requests/162 - IQ3_S_R4.md

0

github-data/pull_requests/163-q4_0_r4_ Use AVX2 version for matrix x vector.md → github-data/pull_requests/163 - q4_0_r4_ Use AVX2 version for matrix x vector.md

0

github-data/pull_requests/168-Falcon3 changes.md → github-data/pull_requests/168 - Falcon3 changes.md

0

github-data/pull_requests/169-Be able to re-quantize MS BitNet I2_S models.md → github-data/pull_requests/169 - Be able to re-quantize MS BitNet I2_S models.md

0

github-data/pull_requests/17-Merge mainline - Aug 12 2024.md → github-data/pull_requests/17 - Merge mainline - Aug 12 2024.md

0

github-data/pull_requests/170-MoE fix for R4 quants.md → github-data/pull_requests/170 - MoE fix for R4 quants.md

0

github-data/pull_requests/171-Fix lower FA performance for even batch sizes.md → github-data/pull_requests/171 - Fix lower FA performance for even batch sizes.md

0

github-data/pull_requests/172-CPU Flash Attention improvements.md → github-data/pull_requests/172 - CPU Flash Attention improvements.md

0

github-data/pull_requests/173-More Flash Attention improvements.md → github-data/pull_requests/173 - More Flash Attention improvements.md

0

github-data/pull_requests/174-On Zen4 repack fp16 models to bf16_r16.md → github-data/pull_requests/174 - On Zen4 repack fp16 models to bf16_r16.md

0

github-data/pull_requests/175-Better BF16 support on AVX2.md → github-data/pull_requests/175 - Better BF16 support on AVX2.md

0

github-data/pull_requests/176-Deepseek V3 support added.md → github-data/pull_requests/176 - Deepseek V3 support added.md

0

github-data/pull_requests/177-Update chat templates.md → github-data/pull_requests/177 - Update chat templates.md

0

github-data/pull_requests/178-Interleave 8 rows (Q8_0, IQ4_XS).md → github-data/pull_requests/178 - Interleave 8 rows _Q8_0_ IQ4_XS_.md

0

github-data/pull_requests/179-Minor performance improvements.md → github-data/pull_requests/179 - Minor performance improvements.md

0

github-data/pull_requests/180-Deepseek MLA Optimizations.md → github-data/pull_requests/180 - Deepseek MLA Optimizations.md

0

github-data/pull_requests/181-Various.md → github-data/pull_requests/181 - Various.md

0

github-data/pull_requests/182-Faster Q4_K_R4 and Q5_K_R4 on AVX2_Zen4.md → github-data/pull_requests/182 - Faster Q4_K_R4 and Q5_K_R4 on AVX2_Zen4.md

0

github-data/pull_requests/184-Deepseek-Lite.md → github-data/pull_requests/184 - Deepseek-Lite.md

0

github-data/pull_requests/185-IQ1_S_R4_ better 1.5 bpw quants.md → github-data/pull_requests/185 - IQ1_S_R4_ better 1.5 bpw quants.md

0

github-data/pull_requests/186-iq1_s_r4_ slightly faster NEON gemm_gemv.md → github-data/pull_requests/186 - iq1_s_r4_ slightly faster NEON gemm_gemv.md

0

github-data/pull_requests/187-IQ1_M_R4_ better 1.75 bpw quants.md → github-data/pull_requests/187 - IQ1_M_R4_ better 1.75 bpw quants.md

0

github-data/pull_requests/188-Add optional MLA.md → github-data/pull_requests/188 - Add optional MLA.md

0

github-data/pull_requests/189-Rename q4_0_r4, q8_0_r4 and iq4_xs_r4 to _r8.md → github-data/pull_requests/189 - Rename q4_0_r4_ q8_0_r4 and iq4_xs_r4 to _r8.md

0

github-data/pull_requests/19-Skip barriers of noops.md → github-data/pull_requests/19 - Skip barriers of noops.md

0

github-data/pull_requests/190-cuda_ non-contiguous rms norm.md → github-data/pull_requests/190 - cuda_ non-contiguous rms norm.md

0

github-data/pull_requests/191-Add additional checks for iq1_s_r4 quantization.md → github-data/pull_requests/191 - Add additional checks for iq1_s_r4 quantization.md

0

github-data/pull_requests/192-Revert #79.md → github-data/pull_requests/192 - Revert _79.md

0

github-data/pull_requests/193-RPC sync.md → github-data/pull_requests/193 - RPC sync.md

0

github-data/pull_requests/194-Use Q8_K_128 for IQ1_S_R4 and IQ1_M_R4 matrix multiplications.md → github-data/pull_requests/194 - Use Q8_K_128 for IQ1_S_R4 and IQ1_M_R4 matrix multiplications.md

0

github-data/pull_requests/195- Deepseek MLA Optimizations V2.md → github-data/pull_requests/195 - Deepseek MLA Optimizations V2.md

0

github-data/pull_requests/197-FA_ Add option to build all FA kernels.md → github-data/pull_requests/197 - FA_ Add option to build all FA kernels.md

0

github-data/pull_requests/198- Load all MoE experts during warmup and make warmup 1 token.md → github-data/pull_requests/198 - Load all MoE experts during warmup and make warmup 1 token.md

0

github-data/pull_requests/2-Offload Bitnet token embeddings to the GPU - the right way.md → github-data/pull_requests/2 - Offload Bitnet token embeddings to the GPU - the right way.md

0

github-data/pull_requests/20-iq2_k_ slightly better bpw - accuracy compromise.md → github-data/pull_requests/20 - iq2_k_ slightly better bpw - accuracy compromise.md

0

github-data/pull_requests/200-DeepSeek FA support (CPU only).md → github-data/pull_requests/200 - DeepSeek FA support _CPU only_.md

0

github-data/pull_requests/202-Fix imatrix overprotectiveness.md → github-data/pull_requests/202 - Fix imatrix overprotectiveness.md

0

github-data/pull_requests/204-Fix iqk_mul_mat on AVX512 systems that are missing BF16 support.md → github-data/pull_requests/204 - Fix iqk_mul_mat on AVX512 systems that are missing BF16 support.md

Some files were not shown because too many files have changed in this diff Show More