| Commit message (Expand) | Author | Files | Lines |
| 2026-06-16 | chore: move sources to src/ with proper names, drop qwen_ prefix | Onur Gündüz | 1 | -3725/+0 |
| 2026-06-16 | cpu: size default threads to cgroup cpu quota, not host core count | Onur Gündüz | 1 | -1/+1 |
| 2026-06-16 | server: register bge-base and bge-large encoders | Onur Gündüz | 1 | -0/+6 |
| 2026-06-15 | server: serve BERT encoders (MiniLM, bge) on /v1/embeddings | Onur Gündüz | 1 | -40/+117 |
| 2026-06-15 | server: guard empty-chunk memcpy and check self-pipe writes | Onur Gündüz | 1 | -4/+12 |
| 2026-06-15 | all: support GTE-Qwen2 embeddings | Onur Gündüz | 1 | -38/+41 |
| 2026-06-15 | server: add Qwen3 text_type query/document instruction hint | Onur Gündüz | 1 | -2/+71 |
| 2026-06-15 | late: add CUDA late-interaction rerank path (GPU encode, host MaxSim) | Onur Gündüz | 1 | -9/+75 |
| 2026-06-15 | late: batch CPU rerank candidate encoding in one packed forward | Onur Gündüz | 1 | -20/+23 |
| 2026-06-15 | late: batch MLX rerank candidate encoding in one padded pass | Onur Gündüz | 1 | -30/+23 |
| 2026-06-15 | chore: run clang-format | Onur Gündüz | 1 | -636/+664 |
| 2026-06-15 | server: version flags, drop cost block, tidy batch-wait note | Onur Gündüz | 1 | -30/+35 |
| 2026-06-14 | server: per-family embedding encoding (Qwen3 float, pplx int8) | Onur Gündüz | 1 | -57/+99 |
| 2026-06-14 | server: add Qwen3-Embedding-8B model slot | Onur Gündüz | 1 | -0/+3 |
| 2026-06-14 | all: add Qwen3-Embedding-4B + fix terminal token | Onur Gündüz | 1 | -6/+8 |
| 2026-06-14 | all: add support for Qwen3-Embedding + causal GQA attention | Onur Gündüz | 1 | -28/+108 |
| 2026-06-14 | docs: fix CLI name in comments | Onur Gündüz | 1 | -4/+1 |
| 2026-06-14 | cli: scope GPU options to their respective build targets | Onur Gündüz | 1 | -68/+77 |
| 2026-06-14 | server: remove CORS support | Onur Gündüz | 1 | -11/+1 |
| 2026-06-14 | cli: remove --backend, use --mlx and --cuda consistently | Onur Gündüz | 1 | -36/+7 |
| 2026-06-14 | server: add late-interaction rerank API | Onur Gündüz | 1 | -42/+595 |
| 2026-06-14 | server: tune admission deadline by backend | Onur Gündüz | 1 | -2/+5 |
| 2026-06-14 | server: make microbatch admission deterministic | Onur Gündüz | 1 | -30/+68 |
| 2026-06-14 | chore: rename project | Onur Gündüz | 1 | -128/+128 |
| 2026-06-14 | server: resolve contextual separator from vocab, test contextual path | Onur Gündüz | 1 | -1/+8 |
| 2026-06-14 | build: rename make targets blas->cpu, mlx->metal, shared->lib | Onur Gündüz | 1 | -2/+2 |
| 2026-06-14 | server: default micro-batch cap to 32; add scheduler sweep driver | Onur Gündüz | 1 | -3/+6 |
| 2026-06-14 | server: do not idle-reap clients with requests in flight | Onur Gündüz | 1 | -1/+4 |
| 2026-06-14 | chore: rename sources; binaries pplx-embed, pplx-embed-server | Onur Gündüz | 1 | -4/+339 |
| 2026-06-14 | gitignore: track new binary and library names | Onur Gündüz | 1 | -0/+0 |
| 2026-06-14 | kernels: drop asr_ prefix naming | Onur Gündüz | 1 | -2/+2 |
| 2026-06-14 | cli: rename flags, add --stream, split serving into pplx-embed-server | Onur Gündüz | 1 | -13/+10 |
| 2026-06-14 | server: fix unused-rc warning in plain BLAS builds | Onur Gündüz | 1 | -1/+2 |
| 2026-06-14 | cuda: add server contextual path | Onur Gündüz | 1 | -1/+74 |
| 2026-06-14 | chore: address static analyzer warnings | Onur Gündüz | 1 | -6/+28 |
| 2026-06-14 | server: expose worker stage timing | Onur Gündüz | 1 | -13/+95 |
| 2026-06-14 | tokenizer: add reusable encode workspace | Onur Gündüz | 1 | -1/+10 |
| 2026-06-14 | server: support http keep-alive | Onur Gündüz | 1 | -11/+98 |
| 2026-06-14 | mlx: add opt-in 8-bit weight quantization | Onur Gündüz | 1 | -1/+15 |
| 2026-06-14 | server: bound mlx batches by padded token rows | Onur Gündüz | 1 | -2/+25 |
| 2026-06-14 | server: reject unsafe mlx model overcommit | Onur Gündüz | 1 | -0/+103 |
| 2026-06-14 | server: simplify context separator logic | Onur Gündüz | 1 | -13/+4 |
| 2026-06-14 | server: batch contextual document inference | Onur Gündüz | 1 | -179/+354 |
| 2026-06-14 | server: batch standard requests by token budget | Onur Gündüz | 1 | -11/+64 |
| 2026-06-14 | server: align embedding quantization with perplexity | Onur Gündüz | 1 | -13/+11 |
| 2026-06-14 | server: support float embedding responses | Onur Gündüz | 1 | -18/+52 |
| 2026-06-14 | server: add embeddings micro-batching | Onur Gündüz | 1 | -98/+343 |
| 2026-06-14 | server: implement HTTP API with libae integration | Onur Gündüz | 1 | -0/+1524 |