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…
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: 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:…
pytorch/pytorch: viable/strict/1788088963: Fix forward AD gradcheck error indexing (#194991)
Summary I reviewed the patch before submission and understand the change as a fix to the forward-AD fast-mode diagnostic path, not the normal gradcheck computation. The technical summary and test notes below were…
pytorch/pytorch: viable/strict/1788078586: [torchcomms hash update] update the pinned torchcomms hash (#195084)
This PR is auto-generated nightly by this action. Update the pinned torchcomms hash. Pull Request resolved: #195084 Approved by: https://github.com/pytorchbot
pytorch/pytorch: trunk/460948b96a67002b7257ac4f3d6a192f70d61d27: [torchcomms hash update] update the pinned torchcomms hash (#195084)
This PR is auto-generated nightly by this action. Update the pinned torchcomms hash. Pull Request resolved: #195084 Approved by: https://github.com/pytorchbot
pytorch/pytorch: trunk/cbb5d2e8abc050fabcda61dcc95cb21d42fb4691: [torchtitan hash update] update the pinned torchtitan hash (#194670)
This PR is auto-generated nightly by this action. Update the pinned torchtitan hash. Pull Request resolved: #194670 Approved by: https://github.com/pytorchbot
pytorch/pytorch: trunk/e24ee98c27bfb1951c2db233d372b9255b2c8512: [vision hash update] update the pinned vision hash (#195085)
This PR is auto-generated nightly by this action. Update the pinned vision hash. Pull Request resolved: #195085 Approved by: https://github.com/pytorchbot
pytorch/pytorch: trunk/2915e67b20beb9ae18027a4300103b3045cfd427: [vllm hash update] update the pinned vllm hash (#194967)
This PR is auto-generated nightly by this action. Update the pinned vllm hash. Pull Request resolved: #194967 Approved by: https://github.com/pytorchbot
pytorch/pytorch: viable/strict/1788076214: Update Metamates merge rule (#195237)
This PR is auto-generated nightly by this action. Updates the Metamates merge rule with active team members. Pull Request resolved: #195237 Approved by: https://github.com/pytorchbot
pytorch/pytorch: trunk/61b129ba9befca712c224057a3468702169e6371: Update Metamates merge rule (#195237)
This PR is auto-generated nightly by this action. Updates the Metamates merge rule with active team members. Pull Request resolved: #195237 Approved by: https://github.com/pytorchbot
ggml-org/llama.cpp: b10689
ggml: allow passing alloc dependencies in graph_optimize (#27301) ggml: allow passing alloc dependencies in graph_optimize add alloc dep tests add TODO about using flat array Website: https://llama.app Attestations:…
pytorch/pytorch: trunk/7e1c35ebdb7015a89ecdb99030893a767550eef1: [CUDA] Add non-overlapping fast path for avg_pool2d backward (#191086)
Summary Adds a dedicated CUDA backward kernel for avg_pool2d when the pooling windows tile the input exactly (stride == kernel_size, no padding, no ceil_mode) -- the common downsampling case such as avg_pool2d(2, 2). In…
pytorch/pytorch: viable/strict/1788067484: [CUDA] Add non-overlapping fast path for avg_pool2d backward (#191086)
Summary Adds a dedicated CUDA backward kernel for avg_pool2d when the pooling windows tile the input exactly (stride == kernel_size, no padding, no ceil_mode) -- the common downsampling case such as avg_pool2d(2, 2). In…
pytorch/pytorch: trunk/10a2f3aa6abef3a84ad0ba37007fbce4d4681a6b: [TokenSwitch] Add symmetric-memory zero-copy dispatch/combine (#187785)
When a dispatch/combine tensor is backed by NCCLSymmetricMemory registered under the process group's name, address it via the registered ncclWindow + offset (RDMA zero-copy path) instead of a plain device pointer,…
pytorch/pytorch: trunk/748dc51db9dd19a621b6dda3d88b48dfe5e8274d
Add parameter-contiguous all-gather (symm_mem.all_gather_offset) (#18…
pytorch/pytorch: viable/strict/1788065415
Add parameter-contiguous all-gather (symm_mem.all_gather_offset) (#18…
ggml-org/llama.cpp: b10688
metal : add fa-vec tunings for M2 (#27940) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43902029 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI…
Loading more...
Showing 1 day · 25 items available