-
Notifications
You must be signed in to change notification settings - Fork 659
Pull requests: google/gemma.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Fix tiled KV cache allocation and support prefix cloning.
#1015
opened Sep 4, 2026 by
copybara-service
Bot
Loading…
Add Highway SIMD logit masking kernel for constrained decoding.
#1014
opened Sep 4, 2026 by
copybara-service
Bot
Loading…
Quantize softmax probabilities S into [0, 255] uint8_t and utilize unsigned-by-signed (uint8 * int8) matrix multiplication for SV accumulation, improving quantization precision. Add SIMD emulation fallback using SumOfMulQuadAccumulate and TableLookupBytes.
#1013
opened Sep 4, 2026 by
copybara-service
Bot
Loading…
Fix crash/abort in matmul when partition size exceeds kMaxNC.
#958
opened Jul 19, 2026 by
copybara-service
Bot
Loading…
Add direct HuggingFace safetensors loader for Gemma 4 (E2B/E4B)
#919
opened May 21, 2026 by
ssfdre38
Loading…
Add configurables for norm/rope/activation/scale/residual connection.
#287
opened Jul 3, 2024 by
copybara-service
Bot
Loading…
ProTip!
no:milestone will show everything without a milestone.