b10361
model : fix SWA not being enabled for EXAONE 4.5 (#26848) model : fix SWA not being enabled for EXAONE 4.5 load_arch_hparams tests hparams.n_layer() == 64 before LLM_KV_NEXTN_PREDICT_LAYERS has been r
Knowledge catalogue
model : fix SWA not being enabled for EXAONE 4.5 (#26848) model : fix SWA not being enabled for EXAONE 4.5 load_arch_hparams tests hparams.n_layer() == 64 before LLM_KV_NEXTN_PREDICT_LAYERS has been r
ggml-webgpu : refactor several wgsl files and simplify flash_attn wgsl. (#26134) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLE
model-saver : fix expert shared/chunk FFN length key clobber (#26693) The saver called add_kv with LLM_KV_EXPERT_SHARED_FEED_FORWARD_LENGTH twice, the second time passing n_ff_chexp. gguf_set_val_u32
model : Granite-Switch Architecture (#25107) granite-switch: add llama.cpp backend (POC, CPU) New 'granite-switch' architecture: a dense, all-attention Granite-4.1 model with N embedded LoRA adapters
vendor : update cpp-httplib to 0.53.0 (#26821) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramewor
model: add MTP support for Nemotron model (#26725) model: add MTP support for Nemotron Nano model model: add mtp_flags for nemotron model address review comments Website: https://llama.app macOS/iOS:
ggml : require contiguous src for ROLL on CUDA and Metal (#25928) ggml_roll only asserts nb[0] == ggml_type_size, so a permuted src is a valid input, but the CUDA and Metal roll kernels index by ne al
ggml-cpu : fix CPU affinity mask being ignored on Android (#26838) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel
llama : support multi-output backend sampling (#25532) Enable backend sampling with token speculation Clamp the mask sum before converting it into the sampled index Add a numeric context parameter dec
ci: rm GGML_HIP_ROCWMMA_FATTN (#26760) Signed-off-by: Aaron Teo aaron.teo1@ibm.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISAB
ggml-cpu : fix missing Q5_0 dispatch in SpaceMiT backend (#26792) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (
CUDA: fix thread/block count in quantized cpy kernel launches (#26731) CUDA: fix thread/block count in quantized cpy kernel launches tests: add uneven block count cpy case Website: https://llama.app m
server: add initial tool isolation support (via docker) (#26507) server: add initial tool isolation support (via docker) add docs adapt get_info py: fix type check cont separate tools_io_sandbox / too
server, ui: only offer a working directory when a tool reads it (#26762) The working directory chip showed up as soon as the server exposed any builtin tool, so a server started with just get_datetime
CUDA: fuse rms_norm + mul + rope (+ view + set_rows) (#26767) CUDA: fuse rms_norm + mul + rope (+ view + set_rows) tests: add broadcast weight case to rms_norm_mul_rope CUDA: check memory ranges befor
server: report the isolate working directory from get_info (#26773) server: report the isolate working directory from get_info Without an explicit cwd, get_info fell back to the server process working
metal : avoid threadgroup matrix array instantiation in kernel_lightning_indexer (#26646) In MSL, declaring an array of matrix types like threadgroup half4x4 causes a 'no matching constructor' compila
cuda: fix warnings for unused variable/function (#26688) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS
sycl : fix error Error OP FLASH_ATTN_EXT on arc770 (#26441) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) i
sycl : Support DSv4 OPs: LIGHTNING_INDEXER,DSV4_HC_COMB,DSV4_HC_POST,DSV4_HC_PRE (#26568) support DSv4 OPs: LIGHTNING_INDEXER,DSV4_HC_COMB,DSV4_HC_POST,DSV4_HC_PREwq update ops.md fix format issue Web
sycl: *glu flat path (#26354) tests: add SWIGLU perf cases perf mode had no GLU coverage. Adds SWIGLU at 17408 columns, 512 and 2048 tokens, f16 and f32, with the operands both fused and split. sycl:
sycl: fix UE4M3 parsing (#25608) The NVFP4 quantization format stores a scaling factor for every group of 16 weights, packed into a single UE4M3 byte. The SYCL GPU code was converting these scale valu
Mitigate crashing issue on Windows MSYS2 UCRT64 environment (GCC 16.1.0) (#26555) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABL
ggml : add aarch64 HWCAP fallbacks and fix fp16 variant detection (#25554) ggml : add fallback definitions for missing aarch64 HWCAP bits ggml : require HWCAP_ASIMDHP for the aarch64 fp16 cpu variants
mtmd: stop feeding the text stream again during Qwen3-TTS generation (#26706) The reference implementation has two mutually exclusive prompt layouts. In non streaming mode the prefill carries the whol
server: (router) do not evict busy models (#26567) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFram
server: (router) add LRU scheduler (#26572) add lru_sched handle coalescing (req leaves waiting queue) add tests fix stream case address review comments Website: https://llama.app macOS/iOS: macOS App
sync : ggml Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu ar
mtmd: fix longest_edge ignoring min/max pixels (#26638) mtmd: fix longest_edge ignoring min/max pixels nits Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64
metal : fix NORM/RMS_NORM for row lengths that leave a partial simdgroup (#26708) ggml_metal_op_norm sized the threadgroup with nth = std::min(nth, args.ne00_t), which can leave nth not a multiple of
sycl: coalesce the ssm_conv window loads (#26612) test-backend-ops perf -o SSM_CONV on an Arc Pro B70, interleaved A/B against master, 6 reps, us/run: ne_a=[515,3328,1,1] ne_b=[4,3328,1,1] n_t=512 97.
tts: account for the vocoder pass in the timings line (#26733) get_output runs the waveform work the pipeline defers to it, from a single trailing window to a full pass depending on the model. Measuri
mtmd/ggml: add ggml_build_forward_order (#26649) ggml: add ggml_build_forward_order ggml_build_forward_expand marks the tensor and all its ancestors for compute, so using it as a pure ordering hint (k
vulkan: fix submission batching size, add debug tools for diagnosing causes of DeviceLost drivers errors (#26371) vulkan: add debug tooling to get more information about a DeviceLost error fix submiss
ci : onboard AMD ROCm CI with gfx1151 fixes (#26544) ci: prepare for amd rocm ci Signed-off-by: Aaron Teo aaron.teo1@ibm.com ci: fix editorconfig-checker Signed-off-by: Aaron Teo aaron.teo1@ibm.com ci
model-loader : fix quantized reshaped tensor strides (#26672) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)
server: fix empty response for /cors-proxy (#26656) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFra
mtmd: add chunk save/load function (#26645) mtmd: add chunk save/load function nits add tests rn _MAX --> _COUNT Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (
Prefer npm ci over install for security (#26601) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramew
build : remove GGML_METAL_USE_BF16 from all build scripts (#26604) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel
vendor : apply patches for subprocess.h (#26606) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramew
server: Adding spec-decode counters to /metrics endpoint (#26389) server: add spec-decode counters to /metrics endpoint server: fixed review comments and now aligned param names exactly with vLLM. Web
fit: Fix memory allocation for MTP layers (#26605) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFram
mtmd: support multi-row batching for deepseek-ocr (#26154) mtmd: support multi-row batching for deepseek-ocr mtmd: weave deepseek-ocr rows in one shot instead of per row (#26615) Co-authored-by: Saba
grammar : degrade max repetition >= 2000 to unbounded (#26613) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64
mtmd: Unlimited-OCR fix max_tiles, setting in converter (#25614) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x
tests: re-enable MiniMax M3 in test-llama-archs (#26633) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS
server: harden the file_glob_search directory walk (#26626) server: don't walk Windows junctions in file_glob_search std::filesystem reports a junction as a plain directory, so the symlink guard misse
ggml: use dynamic allocation for split graph inputs (#22789) ggml: use dynamic allocation for split graph inputs Replace fixed-size GGML_SCHED_MAX_SPLIT_INPUTS arrays with dynamically allocated buffer
vocab : validate default special token ids (#26506) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFra
server: add get_info tool (#26522) server: add get_info tool fix --rpc in docs server: harden get_info probe result handling Report the OS as unknown when the probe process fails to spawn or times out
tests: add model resolution test on synthetic repo listings (#26172) tests: add model resolution test on synthetic repo listings Include download.cpp and arg.cpp inside a namespace with hf_cache monke
model : support MTP in GLM-4.7-Flash (#24868) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework
vendor : update BoringSSL to 0.20260803.0 (#26523) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFram
vendor : update cpp-httplib to 0.52.0 (#26485) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramewor
chat : add new template for DeepSeek V4 Flash 0731 (#26398) common/chat: update DeepSeek V4 templates Align the DeepSeek V4 templates with the official encoders while keeping parser behavior out of th
Extended SYCL oneDNN SDPA to non-FP16 KV caches (Q4_0–Q8_0 and FP32) (#25874) sycl: extend oneDNN SDPA to Q4_0-Q8_0 and F32 KV caches Extends the oneDNN SDPA path (PR #25222) to handle non-F16 KV cach
sycl: parallelize the non-contiguous concat kernel (#25852) sycl: parallelize the non-contiguous concat kernel Launch geometry only: the non-contiguous concat kernel launched a single-lane work-group
llama : move n_vocab from llama_sampler_data to penalty_sampler (#26520) This matches how it is done for logit_bias and mirostat samplers, see #25262 (comment) Website: https://llama.app macOS/iOS: ma
model : allow reshape of tensors during load (#26531) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCF