Default Branch

5f179ff937 · Update README.md · Updated 2026-01-06 04:19:18 -08:00

Branches

4ef2b2852d · server: serve original error for remote models · Updated 2025-09-20 16:46:32 -07:00    pali112

357
1

c10a40db99 · parser: tidy up parameter/message parsing · Updated 2025-09-15 18:09:05 -07:00    pali112

380
1

45fecff6c0 · Revert "runner: simplify parser entrypoints in runner (#12233)" · Updated 2025-09-12 13:31:15 -07:00    pali112

387
1

c0aeb3531b · runner: add sync between computeBatch and completion · Updated 2025-09-10 19:16:28 -07:00    pali112

398
2

f5c9eb5aa2 · models: qwen3vl · Updated 2025-09-10 12:11:46 -07:00    pali112

399
1

02403c2e62 · readme: simplify readme · Updated 2025-09-08 22:13:39 -07:00    pali112

401
1

1fe7e07f63 · sampler/runner: enable gpt-oss structured outputs · Updated 2025-09-03 15:04:20 -07:00    pali112

410
9

1aa4947cdc · Revert "tools: avoid matching braces that are part of tool content (#12039)" · Updated 2025-09-03 15:02:39 -07:00    pali112

410
1

46e485f32c · runner: disable embedding models in ollama engine · Updated 2025-09-02 10:42:16 -07:00    pali112

415
1

8d97d4b0ea · use fs.gguf.File to show models · Updated 2025-08-28 17:30:42 -07:00    pali112

417
3

bdfc82b351 · add model benchmark · Updated 2025-08-25 13:59:44 -07:00    pali112

437
1

d05fc26570 · null truncate · Updated 2025-08-25 10:00:16 -07:00    pali112

425
3

f30d01801d · routes: update generate handler to use runner with harmony · Updated 2025-08-22 16:06:41 -07:00    pali112

438
8

12a7e5ec46 · gemma3: scale in attention · Updated 2025-08-19 13:43:47 -07:00    pali112

437
2

19638cec55 · add docs.json · Updated 2025-08-17 13:12:39 -07:00    pali112

448
1

69f3dfdedf · update tests · Updated 2025-08-14 15:04:26 -07:00    pali112

456
3

087beb40ed · refactor filesForModel · Updated 2025-07-30 13:49:12 -07:00    pali112

495
2

53a53702e0 · gofumpt the file · Updated 2025-07-29 21:37:05 -07:00    pali112

498
3

c8b1f9e1a1 · fix quantization · Updated 2025-07-23 13:14:50 -07:00    pali112

509
3

beaa0e82f3 · api: add flag to disable context shifting · Updated 2025-06-18 17:58:48 -07:00    pali112

570
1