HappyZ happyz
happyz synced commits to refs/pull/19234/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:26 -08:00
7fbd36c50c ggml-webgpu: JIT compile binary operators and handle binding overlaps (#19310)
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
db6adb3c88 tests: reduce number of FA test permutations (#19381)
dfde5993ea common : add common_speculative_is_compat() (#19270)
Compare 8 commits »
happyz synced commits to refs/pull/19170/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:25 -08:00
b83111815e model : support Step3.5-Flash (#19283)
3228e77287 gguf-py : bump sentencepiece version (#19319)
7fbd36c50c ggml-webgpu: JIT compile binary operators and handle binding overlaps (#19310)
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
Compare 7 commits »
happyz synced commits to refs/pull/19183/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:25 -08:00
7fbd36c50c ggml-webgpu: JIT compile binary operators and handle binding overlaps (#19310)
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
db6adb3c88 tests: reduce number of FA test permutations (#19381)
dfde5993ea common : add common_speculative_is_compat() (#19270)
Compare 6 commits »
happyz synced commits to refs/pull/19171/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:25 -08:00
b83111815e model : support Step3.5-Flash (#19283)
3228e77287 gguf-py : bump sentencepiece version (#19319)
7fbd36c50c ggml-webgpu: JIT compile binary operators and handle binding overlaps (#19310)
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
Compare 8 commits »
happyz synced commits to refs/pull/19156/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:24 -08:00
7fbd36c50c ggml-webgpu: JIT compile binary operators and handle binding overlaps (#19310)
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
db6adb3c88 tests: reduce number of FA test permutations (#19381)
dfde5993ea common : add common_speculative_is_compat() (#19270)
Compare 16 commits »
happyz synced commits to refs/pull/19166/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:24 -08:00
7fbd36c50c ggml-webgpu: JIT compile binary operators and handle binding overlaps (#19310)
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
db6adb3c88 tests: reduce number of FA test permutations (#19381)
dfde5993ea common : add common_speculative_is_compat() (#19270)
Compare 6 commits »
happyz synced commits to refs/pull/19167/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:24 -08:00
b83111815e model : support Step3.5-Flash (#19283)
3228e77287 gguf-py : bump sentencepiece version (#19319)
7fbd36c50c ggml-webgpu: JIT compile binary operators and handle binding overlaps (#19310)
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
Compare 8 commits »
happyz synced commits to refs/pull/19148/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:23 -08:00
7fbd36c50c ggml-webgpu: JIT compile binary operators and handle binding overlaps (#19310)
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
db6adb3c88 tests: reduce number of FA test permutations (#19381)
dfde5993ea common : add common_speculative_is_compat() (#19270)
Compare 7 commits »
happyz synced commits to refs/pull/19132/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:12 -08:00
b83111815e model : support Step3.5-Flash (#19283)
3228e77287 gguf-py : bump sentencepiece version (#19319)
7fbd36c50c ggml-webgpu: JIT compile binary operators and handle binding overlaps (#19310)
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
Compare 8 commits »
happyz synced commits to refs/pull/19139/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:12 -08:00
7fbd36c50c ggml-webgpu: JIT compile binary operators and handle binding overlaps (#19310)
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
db6adb3c88 tests: reduce number of FA test permutations (#19381)
dfde5993ea common : add common_speculative_is_compat() (#19270)
Compare 6 commits »
happyz synced commits to refs/pull/19113/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:11 -08:00
b83111815e model : support Step3.5-Flash (#19283)
3228e77287 gguf-py : bump sentencepiece version (#19319)
7fbd36c50c ggml-webgpu: JIT compile binary operators and handle binding overlaps (#19310)
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
Compare 14 commits »
happyz synced commits to refs/pull/19121/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:11 -08:00
b83111815e model : support Step3.5-Flash (#19283)
3228e77287 gguf-py : bump sentencepiece version (#19319)
7fbd36c50c ggml-webgpu: JIT compile binary operators and handle binding overlaps (#19310)
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
Compare 8 commits »
happyz synced commits to refs/pull/19101/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:11 -08:00
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
db6adb3c88 tests: reduce number of FA test permutations (#19381)
dfde5993ea common : add common_speculative_is_compat() (#19270)
06bf3796f4 unicode : MSVC regex fix (#19340)
Compare 5 commits »
happyz synced commits to refs/pull/18993/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:10 -08:00
b83111815e model : support Step3.5-Flash (#19283)
3228e77287 gguf-py : bump sentencepiece version (#19319)
7fbd36c50c ggml-webgpu: JIT compile binary operators and handle binding overlaps (#19310)
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
Compare 8 commits »
happyz synced commits to refs/pull/18981/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:10 -08:00
dd52e3fd0c opencl: refactor cumsum
c4b57de54c remove unused argument
afaf17d767 OpenCL: add CUMSUM op support
b83111815e model : support Step3.5-Flash (#19283)
Compare 52 commits »
happyz synced commits to refs/pull/19098/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:10 -08:00
b83111815e model : support Step3.5-Flash (#19283)
3228e77287 gguf-py : bump sentencepiece version (#19319)
7fbd36c50c ggml-webgpu: JIT compile binary operators and handle binding overlaps (#19310)
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
Compare 8 commits »
happyz synced commits to refs/pull/18981/head at happyz/llama.cpp from mirror 2026-02-06 18:02:10 -08:00
dd52e3fd0c opencl: refactor cumsum
c4b57de54c remove unused argument
afaf17d767 OpenCL: add CUMSUM op support
b83111815e model : support Step3.5-Flash (#19283)
3228e77287 gguf-py : bump sentencepiece version (#19319)
Compare 182 commits »
happyz synced commits to refs/pull/18890/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:09 -08:00
b83111815e model : support Step3.5-Flash (#19283)
3228e77287 gguf-py : bump sentencepiece version (#19319)
7fbd36c50c ggml-webgpu: JIT compile binary operators and handle binding overlaps (#19310)
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
Compare 8 commits »
happyz synced commits to refs/pull/18908/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:09 -08:00
db6adb3c88 tests: reduce number of FA test permutations (#19381)
dfde5993ea common : add common_speculative_is_compat() (#19270)
06bf3796f4 unicode : MSVC regex fix (#19340)
3688c4f504 Kimi-Linear support (backend agnostic + MLA KV cache) (#18755)
Compare 18 commits »
happyz synced commits to refs/pull/18963/merge at happyz/llama.cpp from mirror 2026-02-06 18:02:09 -08:00
537eadb1b9 sycl: add F16 support for GGML_OP_CEIL (#19306)
db6adb3c88 tests: reduce number of FA test permutations (#19381)
dfde5993ea common : add common_speculative_is_compat() (#19270)
06bf3796f4 unicode : MSVC regex fix (#19340)
Compare 34 commits »