]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2025-08-18 Georgi Gerganovscripts : update sync scripts
2025-08-18 Sigbjørn Skjæretllama : merge conts and reshapes and remove unnecessary...
2025-08-18 Georgi Gerganovreadme : update hot topics (#15397)
2025-08-18 davidefserver : fix incoming tasks not process in order (...
2025-08-18 Dobri DanchevFix broken build: require updated pip to support -...
2025-08-18 compiladeggml-quants : fix make_qp_quants NANs and IQ1 assertion...
2025-08-18 Jeff Bolzvulkan: disable spirv-opt for bfloat16 shaders (#15352)
2025-08-17 Oleksandr Kuvshynovserver : export max observed n_past value (#15361)
2025-08-17 Jeff Bolzvulkan: Use larger workgroups for mul_mat_vec when...
2025-08-17 Dong Won Kimvulkan: support sqrt (#15370)
2025-08-17 Sigbjørn Skjæretconvert : force patch_embd weights to F16 or F32 to...
2025-08-17 Sigbjørn Skjæretci : fix hang in windows-hip build/release (#15365)
2025-08-17 Jeff Bolzvulkan: Optimize argsort (#15354)
2025-08-16 Tarek Dakhranmodel : support vision LiquidAI LFM2-VL family (#15347)
2025-08-16 Jeff Bolzvulkan: fuse adds (#15252)
2025-08-16 Jeff Bolzvulkan: Support mul_mat_id with f32 accumulators (...
2025-08-16 Jeff Bolzvulkan: Add missing bounds checking to scalar/coopmat1...
2025-08-16 rmatifOpenCL: add initial FA support (#14987)
2025-08-15 Daniel Beveniuscommon : fix double bos, use common_chat_templates...
2025-08-15 lhezopencl: add initial mxfp4 support via mv (#15270)
2025-08-15 Georgi Gerganovvulkan : fix out-of-bounds access in argmax kernel...
2025-08-15 Georgi Gerganovvulkan : fix compile warnings on macos (#15340)
2025-08-15 Aaron Teoggml: initial IBM zDNN backend (#14975)
2025-08-15 Sigbjørn Skjæretci : fix ios-xcode-build (#15324)
2025-08-15 Diego Devesaci : move ccache action to ggml-org fork (#15328)
2025-08-15 Johannes Gäßlertest-opt: fix backend support check (#15317)
2025-08-14 Johannes GäßlerCUDA: fix negative KV_max values in FA (#15321)
2025-08-14 Georgi Gerganoveval-callback : stop on first NaN (#15320)
2025-08-14 Diego Devesachat : include kwargs in template example (#15309)
2025-08-14 Daniel Beveniusllama : add 18-layer model type for Gemma 3-270m (...
2025-08-14 simevodevops : fix compile bug when the BASE_CUDA_DEV_CONTAIN...
2025-08-14 uvosHIP: Cleanup hipification header (#15285)
2025-08-14 Aldehir Rojasgpt-oss: implement harmony parsing (#15181) upstream/0.0.6164
2025-08-14 Christian Kastnerdocker : Enable GGML_CPU_ALL_VARIANTS for ARM (#15267)
2025-08-14 Georgi Gerganovreadme : update hot topics (#15315)
2025-08-14 Jeff Bolzvulkan: perf_logger improvements (#15246)
2025-08-14 Georgi Gerganovserver : add SWA checkpoints (#15293)
2025-08-14 Georgi Gerganovsync : ggml
2025-08-14 Jason Niggml: fix ggml_conv_1d_dw bug (ggml/1323)
2025-08-14 Georgi Gerganovtests : remove unused includes (ggml/0)
2025-08-14 kallewoofperplexity : provide a helpful hint for has_cpl case...
2025-08-14 Sigbjørn Skjæretcuda : fix GGML_CUDA_GRAPHS=OFF (#15300)
2025-08-14 Jonathan Graehlfinetune: SGD optimizer, more CLI args (#13873)
2025-08-14 kallewoofperplexity: give more information about constraints...
2025-08-13 uvosHIP: bump requirement to rocm 6.1 (#15296)
2025-08-13 Bas Nijholtfix(nix): remove non-functional llama-cpp cachix cache...
2025-08-13 Sigbjørn Skjæretserver : enable -td and -tbd parameters (#15172)
2025-08-13 Juddggml : update `ggml_rope_multi` (#12665)
2025-08-13 Copilot common : add --override-tensor-draft, --cpu-moe-draft...
2025-08-13 Aldehir Rojasserver : filter out harmony thought messages (#15278)
2025-08-13 Ali Tariqci : Added CI with RISC-V RVV1.0 Hardware (#14439)
2025-08-13 Sigbjørn Skjæretci : add more python requirements to copilot-setup...
2025-08-13 Georgi Gerganovggml : repack block_iq4_nlx8 (#14904)
2025-08-13 Oliver SimonsCUDA: Optimize `reduce_rows_f32` kernel, leading up...
2025-08-13 Sigbjørn Skjæretci : add copilot-setup-steps.yml (#15214)
2025-08-13 Tak-RSggml-rpc: chunk send()/recv() to avoid EINVAL for very...
2025-08-12 uvosHIP: disable sync warp shuffel operators from clr amd_w...
2025-08-12 Romain Biessysycl: Fix and disable more configurations of mul_mat...
2025-08-12 rmatifopencl: allow mixed f16/f32 `add` (#15140)
2025-08-12 Aman GuptaCUDA cmake: add `-lineinfo` for easier debug (#15260)
2025-08-12 Chenguang LiCANN: GGML_OP_CPY optimization (#15070)
2025-08-12 R0CKSTARmusa: fix failures in test-backend-ops for mul_mat_id...
2025-08-11 hipuddingCANN: Add broadcast for softmax and FA (#15208)
2025-08-11 rainredmtmd : Fix MinicpmV model converter and clip to avoid...
2025-08-11 Xuan-Son Nguyenchat : hotfix gpt-oss jinja raising an exception (...
2025-08-11 Xuan-Son Nguyenserver : allow specifying reasoning_format in HTTP...
2025-08-11 Zagajreadme : update infra list (#15234)
2025-08-11 Georgi Gerganovkv-cache : fix seq_rm with seq_id == -1 (#15226)
2025-08-11 Daniel Beveniuskv-cache : log (debug) all streams in find_slot (#15176)
2025-08-11 Sigbjørn Skjæretconvert : fix merge conflicts (#15229)
2025-08-11 Daniel Beveniusperplexity : update comments/error msg to use decode...
2025-08-11 Julien Denizeconvert : improve Mistral models integration (#14737)
2025-08-11 Charles Xukleidiai: fix unsigned overflow bug (#15150)
2025-08-09 David Zhaocuda: refactored ssm_scan and use CUB (#13291)
2025-08-09 Aman GuptaCUDA: add attention sinks for tile and wmma (#15178)
2025-08-08 compiladegguf-py : add Numpy MXFP4 de/quantization support ...
2025-08-08 Johannes Gäßlerserver-bench: external OAI servers, sqlite (#15179)
2025-08-08 AN Longggml : fix field name when new ggml_backend (#14944)
2025-08-08 Olivier Chafikvendor: sync minja (#15161)
2025-08-08 Johannes GäßlerCUDA: attention sinks for mma FlashAttention (#15157)
2025-08-08 lhezopencl: support sink in `soft_max` (attn sinks) (#15152)
2025-08-07 Xuan-Son Nguyenconvert : support non-mxfp4 HF model (#15153)
2025-08-07 Jeff Bolzvulkan: support fattn sinks (#15126)
2025-08-07 Jeff Bolzvulkan: Add env var to disable host visible vidmem...
2025-08-07 RunningLeonllama : Support intern-s1 (#14875)
2025-08-07 uvosHIP: add cmake option to enable compiler output of...
2025-08-07 Christian Kastnerggml: Skip backend library linking code when GGML_BACKE...
2025-08-07 Johannes GäßlerCUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 (#15131)
2025-08-07 Johannes Gäßlerscripts: fix crash when --tool is not set (#15133)
2025-08-07 Daniel Beveniusrequirements : fix PyTorch uint64 compatibility (#15134)
2025-08-06 Reese Levineggml: Add basic SET_ROWS support in WebGPU (#15137)
2025-08-06 rmatiffix profiling crash (#15072)
2025-08-06 lhezopencl: add `swiglu_oai` and `add_id` (#15121)
2025-08-06 Sachin Desaichat : support Granite model reasoning and tool call...
2025-08-06 Juk ArmstrongFixed name `-override-tensors` to `-override-tensor...
2025-08-06 Diego Devesaggml : fix fallback to CPU for ununsupported ops (...
2025-08-06 Sigbjørn Skjæretchat : fix yandex chat template (#15116)
2025-08-06 stevenkuangchat : fix hunyuan auto-detection (#15114)
2025-08-06 Chenguang LiCANN: add support for ACL Graph (#15065)
2025-08-05 Reese Levineggml: WebGPU disable SET_ROWS for now (#15078)
next