Understanding ChatGPT Work
OpenAI announced ChatGPT Work on July 9th, and have been furiously iterating on it ever since. It is an extraordinarily confusing and very powerful product. Here's what I've figured out about it so far. ChatGPT Work is…
Daily edition · AI
The daily ledger
TILens turns technical updates into a focused daily brief: official releases, trusted reporting, and practitioner analysis, deduplicated and organized by topic.
ggml-org/llama.cpp: b10705
llama: improve TENSOR_READ_LAZY handling (#27837) force lazy tensor on cpu if lazy is on llama: improve TENSOR_READ_LAZY handling Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestation…
ggml-org/llama.cpp: b10704
CUDA: use the fast mm_ids_helper path for any n_expert_used (#27978) The optimized path grouped warp lanes by token and required warp_size % n_expert_used == 0, with a single hardcoded exception padding 6 up to 8. Every…
ggml-org/llama.cpp: b10703
hip: tune rdna 3 mmq config (#26284) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44012223 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI…
ggml-org/llama.cpp: b10702
hip : optimize Q2_0 dot-product path for gfx1201 (#26753) hip/gfx1201: optimize q2_0 vec_dot_q2_0_q8_1 with native amdgcn perm Broadened HIP's Q2_0 perm optimization Remove redundant HIP perm availability guard Optimize…
ggml-org/llama.cpp: b10701
dflash: pass missing NVFP4 scales to attention operations (#28000) DFlash2 NVFP4 draft models produced almost no accepted speculative tokens because the Q, K, V, and output projection scales were not passed to the…
ggml-org/llama.cpp: b10700
common: rename --tensor-read-lazy to --lazy-mode, add -lzm shorthand (#27969) Rename the --tensor-read-lazy CLI argument to --lazy-mode, to match the internal lazy_mode parameter, and add a -lzm shorthand. Sync the…
ggml-org/llama.cpp: b10699
ggml : add ggml_backend_op_alloc_size_may_expand, use it in RPC (#27960) some backends (Metal, SYCL, WebGPU) require additional memory for fleeting data for certain ops, which is reflected in their get_alloc_size…
ggml-org/llama.cpp: b10698
rpc: fix apple rdma error spew on teardown (#27908) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43970664 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64,…
ggml-org/llama.cpp: b10697
metal: add fa-vec tunings for M3 Ultra (#27999) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43968762 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64,…
ggml-org/llama.cpp: b10696
metal : Add fa-vec tuning for M3 Pro (#27963) Related issue: #27668 Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43966636 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple…
pytorch/pytorch: viable/strict/1788112218: [MPS] Add special_laguerre_polynomial_l (#195225)
I have built and run the tests for this change locally on Apple silicon before submitting. The description below was drafted with an AI assistant, so it is quoted rather than presented as my own prose. Adds a native…
pytorch/pytorch: trunk/4067ee191f69f305d6da99289e9a92c20416f411
[MPS] Resolve compile_shader headers the way cpp_extension does (#195…
pytorch/pytorch: viable/strict/1788110507
[MPS] Resolve compile_shader headers the way cpp_extension does (#195…
ggml-org/llama.cpp: b10695
vendor : update cpp-httplib to 0.54.0 (#27919) vendor : update cpp-httplib to 0.54.0 vendor : update cpp-httplib to 0.54.0 and 0.54.1 Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attesta…
ggml-org/llama.cpp: b10694
rpc : fix pre-rdma macOS versions (#27815) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43962220 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI…
ggml-org/llama.cpp: b10693
hexagon: support for device discovery and create sessions on demand (#27785) hex-devices: add support for lazy session allocation and cleanup dev interfaces Co-authored-by: Marco Colombo mcolombo@qti.qualcomm.com…
ggml-org/llama.cpp: b10692
sycl: split long rows in TOP_K instead of one work-group per row (#27847) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43958406 macOS/iOS: macOS Apple Silicon (arm64) macOS…
ggml-org/llama.cpp: b10691
metal : fix null-pipeline crash for F16 src1 mul_mat/mul_mat_id (#25648) metal : fail closed on mul_mat shapes with missing F16 kernels metal : abort on nil pipeline in encoder_set_pipeline metal : address review…
ggml-org/llama.cpp: b10690
memory : copy Hadamard matrix to k_rot tensor only if it has buffer assigned to prevent crashes during context shift of unquantized K cache (#27967) Co-authored-by: Stanisław Szymczyk sszymczy@gmail.com Co-authored-by:…
Loading more...
Showing 1 day · 45 items available