Commit Graph
67 Commits
Author SHA1 Message Date
Sigbjørn Skjæret 5e1d74043e ci : set run-name for publish release (#30214) 2026-10-09 11:12:24 +02:00
Sigbjørn Skjæret 42b021b4dc vocab : add plamo fim tokens (#30090) 2026-10-07 11:40:35 +02:00
Sigbjørn Skjæret 7049ff0cbe ci : add 1accel label [no ci] (#30016) 2026-10-05 21:52:20 +02:00
Sigbjørn Skjæret 2ed93db472 ci : disable unused qemu in docker build (#29984) 2026-10-05 12:33:10 +02:00
Sigbjørn Skjæret e5983d6704 ci : winget urls must be separate strings (#29978) 2026-10-05 09:36:57 +02:00
Sigbjørn Skjæret 4ca6b76f0b ci : fix docker workflow permissions (#29979) 2026-10-05 09:36:03 +02:00
Sigbjørn Skjæret 2e7c58c547 ci : windows llvm build requires ninja multi-config (#29959) 2026-10-04 19:28:24 +02:00
Sigbjørn Skjæret 7f2dd88b0a ci : add windows arm64 vulkan release (#29954)
* add windows vulkan arm64 release

* add link
2026-10-04 18:46:15 +02:00
Sigbjørn Skjæret 46847e6158 ci : set default permissions (#29945) 2026-10-04 16:13:26 +02:00
Sigbjørn Skjæret 0faee50042 ci : pushing tag needs deploy key (#29937) 2026-10-04 09:45:49 +02:00
Sigbjørn Skjæret f98b31c67e ci : improve release flow (#29913)
* improve release flow

* fix copied typo

* fix permissions
2026-10-04 09:31:24 +02:00
Sigbjørn Skjæret 4ebdf2c74a ci : use t4-medium for cuda jobs (#29842)
[no ci]
2026-10-02 17:31:19 +02:00
Sigbjørn Skjæret ca2e2037b6 jinja : support coerced array attributes (#29574)
* support coerced array attributes

* add tests
2026-09-30 15:33:26 +02:00
Sigbjørn Skjæret 72db1e02ff ci : add models backend check (#29651)
* add models backend check

* t4-medium for faster build
2026-09-30 09:06:24 +02:00
Sigbjørn Skjæret 6fd50a4094 ci : bump ty to 0.0.84 (#29529)
* bump ty to 0.0.84

* fix assertion bug caught by ty
2026-09-27 13:43:08 +02:00
Sigbjørn Skjæret 33c923db1b jinja : add support for dict builtin (#29477)
* add support for dict builtin

* add tests
2026-09-27 13:41:50 +02:00
Sigbjørn Skjæret 81bc6b83f8 jinja : implement sameas test (#29448)
* implement sameas test

* add tests
2026-09-26 10:14:58 +02:00
Sigbjørn Skjæret 86a24a182b jinja : fix compile error (#29468) 2026-09-26 09:43:47 +02:00
Sigbjørn Skjæret a1de614ba3 jinja : support noncall test statements with arg (#29443)
* support noncall test statements with arg

* add tests
2026-09-26 08:56:48 +02:00
Sigbjørn Skjæret b248f4a3c1 gguf-py : ByteLevel processing defaults bos/eos to False (#29422) 2026-09-25 13:59:47 +02:00
Sigbjørn Skjæret d81aef1994 gguf-py : TemplateProcessing has final word on add_special_token (#29417)
* templateprocessing must win over tokenizer config

* remove obsolete override
2026-09-25 11:55:38 +02:00
Sigbjørn Skjæret 26758d38f9 ci : fix build-cmake runner target (#29299) 2026-09-23 12:57:14 +02:00
Sigbjørn Skjæret 86b2daa730 ci : run python (jinja) test (#29302) 2026-09-23 11:49:43 +02:00
Sigbjørn Skjæret ec91ab5add docker : bump cuda to 13.4.1 (#29207) 2026-09-21 13:03:41 +02:00
Sigbjørn Skjæret 542e9202d7 ci : refactor build-self-hosted into backend-specific workflows (#28991)
* refactor build-self-hosted into backends

* update workflow names

* build -> ci

* bump openvino

* trigger on cpu and generic ggml changes
2026-09-21 12:51:53 +02:00
Sigbjørn Skjæret f03cf3e9b8 ci : disable GHA cache for copilot (#29068) 2026-09-18 10:20:53 +02:00
Sigbjørn Skjæret bdcbaaf6e7 ci : bump android-actions/setup-android to 4.0.4 (#29065) 2026-09-18 09:04:14 +02:00
Sigbjørn Skjæret 972d2313bc ci : add missing evict-old-files (#29041) 2026-09-17 19:05:40 +02:00
Sigbjørn SkjæretandGeorgi Gerganov 583926e3ac ci : add self-hosted webgpu to hf-jobs (#28712)
* add self-hosted vulkan and webgpu to hf-jobs

* try t4-medium

* cont : adjust cpu backend threads

* try t4-small again

* restore cm jobs

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-09-16 08:23:58 +02:00
Sigbjørn Skjæret 987498f459 ci : fix android release (#28936) 2026-09-15 10:04:35 +03:00
Sigbjørn Skjæret 7cf1c54a96 ci : reuse build tag name when used instead of safe one (#28911) 2026-09-14 22:21:39 +02:00
Sigbjørn Skjæret 97e4ca7358 models : fix incorrect uses of get_key_or_arr (#28868) 2026-09-14 14:05:37 +03:00
Sigbjørn Skjæret 1aca1f9fcd models : fix mimo2 swa pattern load (#28865) 2026-09-14 14:05:17 +03:00
Sigbjørn Skjæret 37b3a9e0cc ci : remove leftover command (#28839) 2026-09-13 10:41:27 +03:00
Sigbjørn Skjæret ae9afff8d2 jinja : support dot property integer literals (#28817) 2026-09-12 23:49:53 +03:00
Sigbjørn Skjæret 451b89bae0 ci : key cache to sanitizer matrix (#28708) 2026-09-11 07:56:18 +02:00
Sigbjørn Skjæret 52d4268656 ci : add self-hosted-gpu-cuda and server-sanitize to hf-jobs (#28693) 2026-09-10 18:11:32 +02:00
Sigbjørn Skjæret 4b98ab805a py : lower numpy to 2.2.6 (#28654)
* Revert "py : bump numpy to 2.4.6 (#28649)"

This reverts commit 9cf3bf256b.

* bump numpy to 2.2.6
2026-09-09 15:56:27 +02:00
Sigbjørn Skjæret 9cf3bf256b py : bump numpy to 2.4.6 (#28649) 2026-09-09 14:59:37 +02:00
Sigbjørn Skjæret 03fa73cb27 ci : disable npm gha cache (#28600)
* disable npm gha cache

* lies
2026-09-08 14:06:15 +02:00
Sigbjørn Skjæret 67672dc5b7 ci : bump ty to 0.0.78 (#28548)
* bump ty to 0.0.78

* type fixes

* more type fixes

* add --exit-zero-on-warning

* remove Callable again
2026-09-07 21:10:06 +02:00
Sigbjørn Skjæret 5202104b59 caps : recheck typed content if template checks for string (#28511) 2026-09-07 09:14:32 +02:00
Sigbjørn Skjæret 8b4b3558f1 ci : move more jobs to ccache-buckets (#28375)
* move more jobs to ccache-buckets

* add venv deps

* also jq
2026-09-04 15:50:33 +02:00
Sigbjørn Skjæret d5fec32a87 ci : enable hf-jobs on server-cuda (#28258) 2026-09-02 20:13:20 +03:00
Sigbjørn Skjæret dfc29b64eb context : autoscale n_ctx_train when yarn scaling specified (#28030) 2026-09-01 19:59:54 +03:00
Sigbjørn Skjæret f28493c783 models : appropriately flag noscan ssm_a tensors (#28121) 2026-09-01 19:59:15 +03:00
Sigbjørn Skjæret 73159c3039 model : fix gemma4-assistant (#28183) 2026-09-01 19:58:44 +03:00
Sigbjørn Skjæret d11b3cc7ed model : load relevant arrays with n_layer_all (#28173) 2026-09-01 19:58:29 +03:00
Sigbjørn Skjæret 9d817213a0 model : load hparams.n_layer_nextn before n_layer() calls (#28159)
* load hparams.n_layer_nextn before n_layer() calls

* remove duplicate loads
2026-09-01 13:55:45 +02:00
Sigbjørn Skjæret 580e88d8b7 ci : add check for unzip (#28082) 2026-08-31 12:17:51 +02:00
Sigbjørn Skjæret 1a946ec745 pr2wt : use ssh/https remote in worktree depending on base (#27800) 2026-08-27 16:27:17 +03:00
Sigbjørn Skjæret da9b5d68c3 ci : make cache bucket public (#27728)
* check for hf token

* make bucket public
2026-08-26 12:08:23 +02:00
Sigbjørn Skjæret 790b5713ca ci : store ccache on HF buckets (test with cuda-ubuntu for now) (#27699)
* add ccache-buckets action

* use ccache-buckets

* only save on master

* install python3-venv for hip

* add jq and python3 for cuda

* only delete caches older than 5 minutes
2026-08-25 17:28:25 +03:00
Sigbjørn Skjæret 8672290039 sycl : add Q2_K reordered MMVQ and ESIMD kernels (again) (#27490)
* Revert "Revert "sycl : add Q2_K reordered MMVQ and ESIMD kernels (#26336)" (#…"

This reverts commit 7a0e42fd01.

* add gate params
2026-08-22 10:09:26 +03:00
Sigbjørn Skjæret 3aeb924628 readme : fix server badge alt (#27533) 2026-08-22 10:08:07 +03:00
Sigbjørn Skjæret 01ac3ad761 ci : add release attestation url (#27389) 2026-08-19 16:40:47 +02:00
Sigbjørn Skjæret 2e92ecd024 models : remove duplicate metadata load (#27378) 2026-08-19 16:05:50 +02:00
Sigbjørn Skjæret 645ca2834b ci : re-enable release dependency for sycl (#27385) 2026-08-19 16:44:16 +03:00
Sigbjørn Skjæret d8df12ebc4 vocab : support integer tokenizer scores (#27260) 2026-08-17 20:13:15 +02:00
Sigbjørn Skjæret 1d2869c6e5 spec : auto-detect mtp draft model type (#27005) 2026-08-13 13:39:16 +02:00
Sigbjørn Skjæret ece98b87f7 model : disallow integer dflash sliding_window_pattern (#26900)
* fix sliding_window_pattern

* disallow integer pattern
2026-08-12 14:24:10 +03:00
Sigbjørn Skjæret 7b13a8404d ci : add missing release check (#26923) 2026-08-11 21:20:40 +03:00
Sigbjørn Skjæret 70dfba5aee ci : add windows-rocm to check-release (#26897)
[no release]
2026-08-11 17:48:27 +02:00
Sigbjørn Skjæret e5275f6f77 ci : don't specify python version in server-sanitize for broader runner compatibility (#26840)
* don't specify python version for broader runner compatibilty

* run the workflow
2026-08-10 13:32:22 +02:00
Sigbjørn Skjæret eb5667a169 convert : fix DeepseekV4 rope parameters with transformers 5.x (#26673) 2026-08-06 16:06:52 +03:00
Sigbjørn Skjæret cf06ad7dfe vocab : validate plamo2 byte tokens (#26511)
* validate plamo2 byte tokens

* --typo
2026-08-04 11:40:02 +03:00
Sigbjørn Skjæret e8e06f78e2 vocab : validate default special token ids (#26506) 2026-08-03 17:40:53 +02:00