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 7093a35869

commit 0451f10a42

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/discussions/100-New argument _ env variable for GGML_SCHED_MAX_COPIES_.md → github-data/discussions/100 - New argument _ env variable for GGML_SCHED_MAX_COPIES_.md

0

github-data/discussions/104-Convenience improvements for llama-quantize.md → github-data/discussions/104 - Convenience improvements for llama-quantize.md

0

github-data/discussions/140-Questions about weight[j].md → github-data/discussions/140 - Questions about weight_j_.md

0

github-data/discussions/15-Will LQER improve k- and i-quants_.md → github-data/discussions/15 - Will LQER improve k- and i-quants_.md

0

github-data/discussions/164-Latest CPU performance comparison with llama.cpp.md → github-data/discussions/164 - Latest CPU performance comparison with llama.cpp.md

0

github-data/discussions/165-Norm RMS Epsilon.md → github-data/discussions/165 - Norm RMS Epsilon.md

0

github-data/discussions/166-Learning more LLM quantization.md → github-data/discussions/166 - Learning more LLM quantization.md

0

github-data/discussions/18-CPU beating GPU in token generation speed.md → github-data/discussions/18 - CPU beating GPU in token generation speed.md

0

github-data/discussions/201-What is the NUMA situation _.md → github-data/discussions/201 - What is the NUMA situation _.md

0

github-data/discussions/211-help me create an importance matrix primer.md → github-data/discussions/211 - help me create an importance matrix primer.md

0

github-data/discussions/223-Recent performance testing with DeepSeek R1.md → github-data/discussions/223 - Recent performance testing with DeepSeek R1.md

0

github-data/discussions/242-Switching from llama.cpp_ktransformers, seeking advice_guidance.md → github-data/discussions/242 - Switching from llama.cpp_ktransformers_ seeking advice_guidance.md

0

github-data/discussions/25-CPU prompt processing speed for large contexts.md → github-data/discussions/25 - CPU prompt processing speed for large contexts.md

0

github-data/discussions/256-Diverging from llama.cpp.md → github-data/discussions/256 - Diverging from llama.cpp.md

0

github-data/discussions/258-Quick-start Guide coming over from llama.cpp and ktransformers!.md → github-data/discussions/258 - Quick-start Guide coming over from llama.cpp and ktransformers_.md

0

github-data/discussions/266-Benchmarking DeepSeek R1 - 16x3090.md → github-data/discussions/266 - Benchmarking DeepSeek R1 - 16x3090.md

0

github-data/discussions/286-Testing `deepseek-ai_DeepSeek-V3-0324` model support..md → github-data/discussions/286 - Testing _deepseek-ai_DeepSeek-V3-0324_ model support..md

0

github-data/discussions/288-On @compilade's PR 12557 and @jukofyork's quantization ideas.md → github-data/discussions/288 - On _compilade_s PR 12557 and _jukofyork_s quantization ideas.md

0

github-data/discussions/316-Mainline is now copying stuff from ik_llama.cpp.md → github-data/discussions/316 - Mainline is now copying stuff from ik_llama.cpp.md

0

github-data/discussions/319-KTransformers copying ik_llama.cpp.md → github-data/discussions/319 - KTransformers copying ik_llama.cpp.md

0

github-data/discussions/323-Is there an easy way to repack an existing GGUF so it could be used without --run-time-repack (thus enabling mmap).md → github-data/discussions/323 - Is there an easy way to repack an existing GGUF so it could be used wit.md

0

github-data/discussions/334-`iq4_ks` performs great on gemma-3-27b-it-qat-q4_0-unquantized.md → github-data/discussions/334 - _iq4_ks_ performs great on gemma-3-27b-it-qat-q4_0-unquantized.md

0

github-data/discussions/350-Maverick slow prompt with gpu.md → github-data/discussions/350 - Maverick slow prompt with gpu.md

0

github-data/discussions/354-Not all MLAs are born equal.md → github-data/discussions/354 - Not all MLAs are born equal.md

0

github-data/discussions/357-Qwen3 - early performance comparisons.md → github-data/discussions/357 - Qwen3 - early performance comparisons.md

0

github-data/discussions/359-Qwen3 quantization experiments.md → github-data/discussions/359 - Qwen3 quantization experiments.md

0

github-data/discussions/372-multy gpu.md → github-data/discussions/372 - multy gpu.md

0

github-data/discussions/384-ik_llama.cpp issues on an old workstation.md → github-data/discussions/384 - ik_llama.cpp issues on an old workstation.md

0

github-data/discussions/385-Qwen3 235B performance on Intel Xeon Scalable processor.md → github-data/discussions/385 - Qwen3 235B performance on Intel Xeon Scalable processor.md

0

github-data/discussions/393-Creating quantized models.md → github-data/discussions/393 - Creating quantized models.md

0

github-data/discussions/395-Why does imatrix not tokenize special tokens_.md → github-data/discussions/395 - Why does imatrix not tokenize special tokens_.md

0

github-data/discussions/396-Best settings for Maverick - Dual CPU Xeon 8480+ - RTX 3090.md → github-data/discussions/396 - Best settings for Maverick - Dual CPU Xeon 8480_ - RTX 3090.md

0

github-data/discussions/397-KV split while using `-sm row`.md → github-data/discussions/397 - KV split while using _-sm row_.md

0

github-data/discussions/399-Qwen 30b.A3b IK_LCPP comparisons on lowspec machine.md → github-data/discussions/399 - Qwen 30b.A3b IK_LCPP comparisons on lowspec machine.md

0

github-data/discussions/401-install bitnet (or other cpu models) on a fresh termux aarch64.md → github-data/discussions/401 - install bitnet _or other cpu models_ on a fresh termux aarch64.md

0

github-data/discussions/403-Tool Calling and Structured Response (Json Mode) support.md → github-data/discussions/403 - Tool Calling and Structured Response _Json Mode_ support.md

0

github-data/discussions/434-Quant Cookers Basic Guide.md → github-data/discussions/434 - Quant Cookers Basic Guide.md

0

github-data/discussions/451-Context reuse _ context shift for long prompts.md → github-data/discussions/451 - Context reuse _ context shift for long prompts.md

0

github-data/discussions/459-qwen3 metrics on ancient hardware (2x xeon Vs 2x P100).md → github-data/discussions/459 - qwen3 metrics on ancient hardware _2x xeon Vs 2x P100_.md

0

github-data/discussions/466-A curiosity..md → github-data/discussions/466 - A curiosity..md

0

github-data/discussions/477-DeepSeek-R1-0528 ik quants!.md → github-data/discussions/477 - DeepSeek-R1-0528 ik quants_.md

0

github-data/discussions/491--rtr actually hurts prompt t_s for large ubatch_.md → github-data/discussions/491 - -rtr actually hurts prompt t_s for large ubatch_.md

0

github-data/discussions/519-Android Build.md → github-data/discussions/519 - Android Build.md

0

github-data/discussions/526-Partial requant feature to save compute and time during tests..md → github-data/discussions/526 - Partial requant feature to save compute and time during tests..md

0

github-data/discussions/532-Guidance on GPU Layer Offloading Strategy in ik_llama.cpp for Multi GPU Rig (2x5090 + 2x4090).md → github-data/discussions/532 - Guidance on GPU Layer Offloading Strategy in ik_llama.cpp for Multi GPU.md

0

github-data/discussions/543-dots.llm1 support and thanks.md → github-data/discussions/543 - dots.llm1 support and thanks.md

0

github-data/discussions/545-Vulkan support_.md → github-data/discussions/545 - Vulkan support_.md

0

github-data/discussions/548-Poor performance with bf16 model on Qwen3 30B-A3B.md → github-data/discussions/548 - Poor performance with bf16 model on Qwen3 30B-A3B.md

0

github-data/discussions/556-ik_llama.cpp for Armv8.0.md → github-data/discussions/556 - ik_llama.cpp for Armv8.0.md

0

github-data/discussions/562-AMD GPU Vulkan & ROCm_HIP Discussion.md → github-data/discussions/562 - AMD GPU Vulkan _ ROCm_HIP Discussion.md

0

github-data/discussions/564-Maybe an interesting CUDA PR here..md → github-data/discussions/564 - Maybe an interesting CUDA PR here..md

0

github-data/discussions/586-Slow KV cache rm operation.md → github-data/discussions/586 - Slow KV cache rm operation.md

0

github-data/discussions/590-How important is Vulkan back-end development_.md → github-data/discussions/590 - How important is Vulkan back-end development_.md

0

github-data/discussions/591-I dont see any speed improvement in generation, so want to understand if i am missing something.md → github-data/discussions/591 - I dont see any speed improvement in generation_ so want to understand i.md

0

github-data/discussions/594-Is AVX2 a hard requirement on x64_.md → github-data/discussions/594 - Is AVX2 a hard requirement on x64_.md

0

github-data/discussions/599-mla matrix absorbtion.md → github-data/discussions/599 - mla matrix absorbtion.md

0

github-data/discussions/613-Pathological Quant_CUDA combinations -- How to know what works_.md → github-data/discussions/613 - Pathological Quant_CUDA combinations -- How to know what works_.md

0

github-data/discussions/619-gpu p2p utilization.md → github-data/discussions/619 - gpu p2p utilization.md

0

github-data/discussions/621-Deepseek v3_r1 poisoned prompt_.md → github-data/discussions/621 - Deepseek v3_r1 poisoned prompt_.md

0

github-data/discussions/623-Quantizing panels_bundles instead of blocks_.md → github-data/discussions/623 - Quantizing panels_bundles instead of blocks_.md

0

github-data/discussions/63-LLaMA-3.2 quantization evaluation.md → github-data/discussions/63 - LLaMA-3.2 quantization evaluation.md

0

github-data/discussions/8-New quantization types IQ2_K, IQ3_K, IQ4_K, IQ5_K.md → github-data/discussions/8 - New quantization types IQ2_K_ IQ3_K_ IQ4_K_ IQ5_K.md

0

github-data/discussions/82-4bpw GGML TYPE_.md → github-data/discussions/82 - 4bpw GGML TYPE_.md

0

github-data/discussions/95-Bitnet.md → github-data/discussions/95 - Bitnet.md

0

github-data/issues/103-Bug_ K cache without FA.md → github-data/issues/103 - Bug_ K cache without FA.md

0

github-data/issues/133-Refactor_ update ggml library_.md → github-data/issues/133 - Refactor_ update ggml library_.md

0

github-data/issues/159-Feature Request_ steps how to compile as cmake i struction on the origi al repo not work here..md → github-data/issues/159 - Feature Request_ steps how to compile as cmake i struction on the origi.md

0

github-data/issues/160-Bug_ Can't compile on MSVC 2022.md → github-data/issues/160 - Bug_ Can_t compile on MSVC 2022.md

0

github-data/issues/167-Bug_ Unable to quantize Falcon 10B 1.58 bitnet model.md → github-data/issues/167 - Bug_ Unable to quantize Falcon 10B 1.58 bitnet model.md

0

github-data/issues/183-Refactor_ iqk_mul_mat.md → github-data/issues/183 - Refactor_ iqk_mul_mat.md

0

github-data/issues/196-Refactor_ remove usage of Q8_1 for activation quantization.md → github-data/issues/196 - Refactor_ remove usage of Q8_1 for activation quantization.md

0

github-data/issues/199-Bug_ Changing system_prompt on llama-server at runtime breaks parallel processing.md → github-data/issues/199 - Bug_ Changing system_prompt on llama-server at runtime breaks parallel .md

0

github-data/issues/203-Bug_ Compliation Error for Intel(R) Xeon(R) Gold 6326 CPU.md → github-data/issues/203 - Bug_ Compliation Error for Intel_R_ Xeon_R_ Gold 6326 CPU.md

0

github-data/issues/209-Does the iqk_mul_mat.cpp support 1.58-bit quantization model_.md → github-data/issues/209 - Does the iqk_mul_mat.cpp support 1.58-bit quantization model_.md

0

github-data/issues/214-AVX512 build error.md → github-data/issues/214 - AVX512 build error.md

0

github-data/issues/217-Bug_ CPU FA with fp16 K-cache is broken.md → github-data/issues/217 - Bug_ CPU FA with fp16 K-cache is broken.md

0

github-data/issues/224-Bug_ IQK_FA_ALL_QUANTS causes failure to compile.md → github-data/issues/224 - Bug_ IQK_FA_ALL_QUANTS causes failure to compile.md

0

github-data/issues/227-Prevent FA usage on CUDA when K and V head sizes are different.md → github-data/issues/227 - Prevent FA usage on CUDA when K and V head sizes are different.md

0

github-data/issues/228-Feature Request_ create tool to offline repack models.md → github-data/issues/228 - Feature Request_ create tool to offline repack models.md

0

github-data/issues/230-Weird assert when using online repacking.md → github-data/issues/230 - Weird assert when using online repacking.md

0

github-data/issues/245-Bug_ Perplexity returns NaN with IQ4_KSS quantisation.md → github-data/issues/245 - Bug_ Perplexity returns NaN with IQ4_KSS quantisation.md

0

github-data/issues/249-CUDA_ results for MoE models are not reproducible.md → github-data/issues/249 - CUDA_ results for MoE models are not reproducible.md

0

github-data/issues/254-Split-mode row.md → github-data/issues/254 - Split-mode row.md

0

github-data/issues/255-Feature Request_ dynamic layer by layer offloading during prompt processing for VRAM constrained scenarios.md → github-data/issues/255 - Feature Request_ dynamic layer by layer offloading during prompt proces.md

0

github-data/issues/257-Bug_ mla=2 in llama-server will crash when request done.md → github-data/issues/257 - Bug_ mla_2 in llama-server will crash when request done.md

0

github-data/issues/26-Feature Request_ Improve CPU processing speed for large contexts.md → github-data/issues/26 - Feature Request_ Improve CPU processing speed for large contexts.md

0

github-data/issues/263-Benchmarking DeepSeek R1 - 16x3090.md → github-data/issues/263 - Benchmarking DeepSeek R1 - 16x3090.md

0

github-data/issues/267-Feature Request_ HugePage mmap alloc for DeepSeek V3_R1.md → github-data/issues/267 - Feature Request_ HugePage mmap alloc for DeepSeek V3_R1.md

0

github-data/issues/271-Possible regression computing `wk_b` tensors on the fly after PR #265.md → github-data/issues/271 - Possible regression computing _wk_b_ tensors on the fly after PR _265.md

0

github-data/issues/281-Bug_ Strange dips in TG performance.md → github-data/issues/281 - Bug_ Strange dips in TG performance.md

0

github-data/issues/285-llama-perplexity giving all NaNs on unsloth Q8_0 quant.md → github-data/issues/285 - llama-perplexity giving all NaNs on unsloth Q8_0 quant.md

0

github-data/issues/29-Bug_ some ifdefs missing in ggml_src_iqk_iqk_quantize.cpp.md → github-data/issues/29 - Bug_ some ifdefs missing in ggml_src_iqk_iqk_quantize.cpp.md

0

github-data/issues/293-Feature Request_ IQ6_K row interleaved quant.md → github-data/issues/293 - Feature Request_ IQ6_K row interleaved quant.md

0

github-data/issues/296-Possible numerical stability issue with experimental quant of DeepSeek-V3-0324_.md → github-data/issues/296 - Possible numerical stability issue with experimental quant of DeepSeek-.md

0

github-data/issues/297-Update gguf-py scripts to support new quant types..md → github-data/issues/297 - Update gguf-py scripts to support new quant types..md

0

github-data/issues/30-Bug_ Appcrash on Windows 7 with GGML_USE_IQK_MULMAT.md → github-data/issues/30 - Bug_ Appcrash on Windows 7 with GGML_USE_IQK_MULMAT.md

0

github-data/issues/300-Bug_ IQK_FA_ALL_QUANTS causes failure to compile.md → github-data/issues/300 - Bug_ IQK_FA_ALL_QUANTS causes failure to compile.md

0

github-data/issues/305-Gibberish output when using DeepSeek-V3-0324-IQ2_K_R4 on mixed CPU + 4 GPUs with -mla (1 or 2).md → github-data/issues/305 - Gibberish output when using DeepSeek-V3-0324-IQ2_K_R4 on mixed CPU _ 4 .md

0

github-data/issues/306-Confused by the -mla flag. What's supported_.md → github-data/issues/306 - Confused by the -mla flag. What_s supported_.md

0

github-data/issues/308-Bug_ Compiling for arm64, error_ cannot convert ‘const uint32x4_t’ to ‘uint8x16_t’ and similar errors.md → github-data/issues/308 - Bug_ Compiling for arm64_ error_ cannot convert _const uint32x4_t_ to _.md

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