HappyZ happyz
happyz synced commits to refs/pull/18892/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:22 -08:00
05fa625eac convert : add JoyAI-LLM-Flash (#19651)
d612901116 perplexity: add proper batching (#19661)
cceb1b4e33 common : inline functions (#18639)
d23a55997d ggml : make `ggml_is_view` as API (#19539)
Compare 40 commits »
happyz synced commits to refs/pull/18817/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:21 -08:00
05fa625eac convert : add JoyAI-LLM-Flash (#19651)
d612901116 perplexity: add proper batching (#19661)
cceb1b4e33 common : inline functions (#18639)
d23a55997d ggml : make `ggml_is_view` as API (#19539)
Compare 40 commits »
happyz synced commits to refs/pull/18859/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:21 -08:00
05fa625eac convert : add JoyAI-LLM-Flash (#19651)
d612901116 perplexity: add proper batching (#19661)
cceb1b4e33 common : inline functions (#18639)
d23a55997d ggml : make `ggml_is_view` as API (#19539)
Compare 7 commits »
happyz synced commits to refs/pull/18862/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:21 -08:00
d612901116 perplexity: add proper batching (#19661)
cceb1b4e33 common : inline functions (#18639)
d23a55997d ggml : make `ggml_is_view` as API (#19539)
5f28c53d11 model: Add support for Tiny Aya Models (#19611)
Compare 7 commits »
happyz synced commits to refs/pull/18784/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:20 -08:00
05fa625eac convert : add JoyAI-LLM-Flash (#19651)
d612901116 perplexity: add proper batching (#19661)
cceb1b4e33 common : inline functions (#18639)
d23a55997d ggml : make `ggml_is_view` as API (#19539)
Compare 7 commits »
happyz synced commits to refs/pull/18816/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:20 -08:00
05fa625eac convert : add JoyAI-LLM-Flash (#19651)
d612901116 perplexity: add proper batching (#19661)
cceb1b4e33 common : inline functions (#18639)
d23a55997d ggml : make `ggml_is_view` as API (#19539)
Compare 9 commits »
happyz synced commits to refs/pull/18742/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:19 -08:00
d612901116 perplexity: add proper batching (#19661)
cceb1b4e33 common : inline functions (#18639)
d23a55997d ggml : make `ggml_is_view` as API (#19539)
5f28c53d11 model: Add support for Tiny Aya Models (#19611)
Compare 22 commits »
happyz synced commits to refs/pull/18745/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:19 -08:00
d612901116 perplexity: add proper batching (#19661)
cceb1b4e33 common : inline functions (#18639)
d23a55997d ggml : make `ggml_is_view` as API (#19539)
5f28c53d11 model: Add support for Tiny Aya Models (#19611)
Compare 7 commits »
happyz synced commits to refs/pull/17924/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:18 -08:00
d612901116 perplexity: add proper batching (#19661)
cceb1b4e33 common : inline functions (#18639)
d23a55997d ggml : make `ggml_is_view` as API (#19539)
5f28c53d11 model: Add support for Tiny Aya Models (#19611)
Compare 23 commits »
happyz synced commits to refs/pull/18059/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:18 -08:00
05fa625eac convert : add JoyAI-LLM-Flash (#19651)
d612901116 perplexity: add proper batching (#19661)
cceb1b4e33 common : inline functions (#18639)
d23a55997d ggml : make `ggml_is_view` as API (#19539)
Compare 8 commits »
happyz synced commits to refs/pull/18675/head at happyz/llama.cpp from mirror 2026-02-16 18:01:18 -08:00
4580fce1c7 Replace reasoning and content analysis with PEG-parser-based
a17950fb63 Extra context for chat templates
6e42723899 Fix templates for server tests
a3e07b3252 Revert bad conversion code [no ci]
562fe10dd5 Add proper reasoning detection for cli
Compare 51 commits »
happyz synced commits to refs/pull/18495/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:18 -08:00
4408494144 build : rework llama_option_depr to handle LLAMA_CURL (#19658)
2ba9adc093 Adjust workaround for ROCWMMA_FATTN/GFX9 to only newer ROCm veresions (#19591)
cc45f2ada6 models : deduplicate delta-net graphs for Qwen family (#19597)
d5dfc33027 graph : fix KQ mask, lora, cvec reuse checks (#19644)
Compare 27 commits »
happyz synced commits to refs/pull/18675/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:18 -08:00
4580fce1c7 Replace reasoning and content analysis with PEG-parser-based
05fa625eac convert : add JoyAI-LLM-Flash (#19651)
a17950fb63 Extra context for chat templates
6e42723899 Fix templates for server tests
Compare 52 commits »
happyz synced commits to refs/pull/17400/head at happyz/llama.cpp from mirror 2026-02-16 18:01:17 -08:00
0031b41ed9 Merge remote-tracking branch 'sfallah/master' into sf/deepseek-ocr
2ba9adc093 Adjust workaround for ROCWMMA_FATTN/GFX9 to only newer ROCm veresions (#19591)
cc45f2ada6 models : deduplicate delta-net graphs for Qwen family (#19597)
d5dfc33027 graph : fix KQ mask, lora, cvec reuse checks (#19644)
267ba5a1d9 ggml: aarch64: Implement SVE in Gemm q4_k 8x8 q8_k Kernel (#19132)
Compare 69 commits »
happyz synced commits to refs/pull/17400/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:17 -08:00
05fa625eac convert : add JoyAI-LLM-Flash (#19651)
d612901116 perplexity: add proper batching (#19661)
cceb1b4e33 common : inline functions (#18639)
d23a55997d ggml : make `ggml_is_view` as API (#19539)
Compare 44 commits »
happyz synced commits to refs/pull/17791/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:17 -08:00
05fa625eac convert : add JoyAI-LLM-Flash (#19651)
d612901116 perplexity: add proper batching (#19661)
cceb1b4e33 common : inline functions (#18639)
d23a55997d ggml : make `ggml_is_view` as API (#19539)
Compare 7 commits »
happyz synced commits to refs/pull/17795/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:17 -08:00
05fa625eac convert : add JoyAI-LLM-Flash (#19651)
d612901116 perplexity: add proper batching (#19661)
cceb1b4e33 common : inline functions (#18639)
d23a55997d ggml : make `ggml_is_view` as API (#19539)
Compare 7 commits »
happyz synced commits to refs/pull/16743/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:16 -08:00
d612901116 perplexity: add proper batching (#19661)
cceb1b4e33 common : inline functions (#18639)
d23a55997d ggml : make `ggml_is_view` as API (#19539)
5f28c53d11 model: Add support for Tiny Aya Models (#19611)
Compare 61 commits »
happyz synced commits to refs/pull/16611/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:16 -08:00
05fa625eac convert : add JoyAI-LLM-Flash (#19651)
d612901116 perplexity: add proper batching (#19661)
cceb1b4e33 common : inline functions (#18639)
d23a55997d ggml : make `ggml_is_view` as API (#19539)
Compare 9 commits »
happyz synced commits to refs/pull/16609/merge at happyz/llama.cpp from mirror 2026-02-16 18:01:16 -08:00
05fa625eac convert : add JoyAI-LLM-Flash (#19651)
d612901116 perplexity: add proper batching (#19661)
cceb1b4e33 common : inline functions (#18639)
d23a55997d ggml : make `ggml_is_view` as API (#19539)
Compare 9 commits »