Default Branch

main 0aa8b371dd · model: add Qwen2.5-VL support (#10385) · Updated 2025-05-14 03:58:02 +00:00

ZIP  TAR.GZ

Branches

tool-parsing 8ed95a4e96 · add tests, organize, comments · Updated 2025-05-14 00:44:47 +00:00    jeans	1 11	Compare	ZIP  TAR.GZ
jessegross/post_predict 5e8041f59b · llm: Make "POST predict" error message more informative · Updated 2025-05-14 00:26:46 +00:00    jeans	2 1	Compare	ZIP  TAR.GZ
jessegross/vision_graph 1089c2a074 · llm: Estimate projector memory correctly for Ollama engine · Updated 2025-05-13 23:44:27 +00:00    jeans	2 2	Compare	ZIP  TAR.GZ
jmorganca/qwen25vl 5c76074f66 · wip · Updated 2025-05-13 02:15:42 +00:00    jeans	11 57	Compare	ZIP  TAR.GZ
drifkin/thinking-api-support bc8abf7917 · WIP thinking API support · Updated 2025-05-13 00:23:41 +00:00    jeans	56 1	Compare	ZIP  TAR.GZ
jessegross/worst-multimodal 0404eae3da · ollamarunner: Multi-modal worst case graph · Updated 2025-05-12 23:35:02 +00:00    jeans	9 3	Compare	ZIP  TAR.GZ
drifkin/array-head-count-simple 20c5fd39c8 · Merge branch 'main' into drifkin/array-head-count-simple · Updated 2025-05-08 18:46:52 +00:00    jeans	22 3	Compare	ZIP  TAR.GZ
brucemacd/model-forward-test-ext 715952705e · model: framework for testing forward pass · Updated 2025-05-08 16:25:12 +00:00    jeans	24 1	Compare	ZIP  TAR.GZ
parth/python-function-parsing 23e8ac9428 · wip? · Updated 2025-05-08 02:00:44 +00:00    jeans	71 2	Compare	ZIP  TAR.GZ
mxyng/qwen3 1546bc4767 · feat: qwen3 dense · Updated 2025-05-07 21:03:27 +00:00    jeans	26 1	Compare	ZIP  TAR.GZ
mxyng/multiple-eos-tokens 855de683ca · get eos_token_id from generation_config.json · Updated 2025-05-06 06:51:35 +00:00    jeans	36 1	Compare	ZIP  TAR.GZ
jmorganca/cuda-compression-none a0a1fb463a · build: disable cuda compression · Updated 2025-05-05 18:20:57 +00:00    jeans	38 1	Compare	ZIP  TAR.GZ
drifkin/num-parallel 67335dede2 · lower default NUM_PARALLEL to 2 · Updated 2025-04-29 09:03:51 +00:00    jeans	67 1	Compare	ZIP  TAR.GZ
drifkin/chat-truncation-fix d20cd8df80 · fix incorrect chat truncation · Updated 2025-04-28 23:11:36 +00:00    jeans	71 1	Compare	ZIP  TAR.GZ
jmorganca/sync f4ab82f0b4 · llama: sync · Updated 2025-04-25 23:38:05 +00:00    jeans	88 1	Compare	ZIP  TAR.GZ
mxyng/parallel-write-blobs 34ae8077d1 · wip: write tensors in parallel · Updated 2025-04-25 20:39:12 +00:00    jeans	90 3	Compare	ZIP  TAR.GZ
parth/python-tools-calling b4cd1118ab · checkpoint for vscode · Updated 2025-04-25 01:23:23 +00:00    jeans	122 4	Compare	ZIP  TAR.GZ
drifkin/array-head-count 7c94471d38 · ggml: more accurate estimates for head count array case · Updated 2025-04-10 23:28:34 +00:00    jeans	122 2	Compare	ZIP  TAR.GZ
brucemacd/create-no-loop 04950140ec · server: do not attempt to parse offset file as gguf · Updated 2025-04-09 16:41:46 +00:00    jeans	125 1	Compare	ZIP  TAR.GZ
parth/server-enable-content-stream-with-tools 3bc9d42e2e · rebase + fix tests · Updated 2025-04-04 00:31:21 +00:00    jeans	139 2	Compare	ZIP  TAR.GZ