happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
8,111 Commits 541 Branches 5,564 Tags 1.4 GiB
Commit Graph

374 Commits

Author SHA1 Message Date
Leszek Hanusz fd3cb9bbdd Merge branch 'master' into notebook 2026-02-17 01:57:31 +01:00
Leszek Hanusz 2377b8c81e Merge branch 'master' into notebook 2026-02-16 02:22:25 +01:00
Adrien Gallouët 9e118b97c4
build : remove LLAMA_HTTPLIB option (#19623) 
This option was introduced as a workaround because cpp-httplib could not
build on visionOS. Since it has been fixed and now compiles on all platforms,
we can remove it and simplify many things.

Signed-off-by: Adrien Gallouët <angt@huggingface.co>
 2026-02-15 15:38:50 +01:00
Aleksander Grygier baa12f3831
webui: Architecture and UI improvements (#19596) 2026-02-14 09:06:41 +01:00
Aleksander Grygier 5174d7206f
webui: UI and routing fixes (#19586) 
* chore: update webui build output

* chore: update webui build output

* fix: Scroll issues in DropdownMenuSearchable

* webui: fix redirect to root ignoring base path

* fix: Word wrapping

* fix: remove obsolete modality UI tests causing CI failures

- Remove VisionModality/AudioModality test stories
- Remove mockServerProps usage and imports
- Simplify Default test (remove dropdown interaction checks)
- Simplify FileAttachments test (remove mocks)

* feat: Improve formatting performance time

---------

Co-authored-by: Pascal <admin@serveurperso.com>
 2026-02-13 12:31:00 +01:00
Aleksander Grygier 4c61875bf8
webui: Add switcher to Chat Message UI to show raw LLM output (#19571) 2026-02-12 19:55:51 +01:00
Aleksander Grygier 4d688f9ebb
(webui) FEATURE: Enable adding or injecting System Message into chat (#19556) 
* feat: Enable adding System Prompt per-chat

* fix: Save draft message in Chat Form when adding System Prompt from new chat view

* fix: Proper system message deletion logic

* chore: Formatting

* chore: update webui build output
 2026-02-12 13:56:08 +01:00
Aleksander Grygier f486ce9f30
(webui) REFACTOR: UI primitives and polish (#19551) 
* webui: UI primitives and polish (non-MCP)

* chore: update webui build output
 2026-02-12 12:21:00 +01:00
Aleksander Grygier 38adc7d469
WebUI Architecture Cleanup (#19541) 
* webui: architecture foundation (non-MCP core refactors)

* chore: update webui build output
 2026-02-12 11:22:27 +01:00
RichardScottOZ fa16e517a3
server : fix typo in README.md for features list (#19510) 
extra l for full
 2026-02-12 08:56:25 +01:00
Leszek Hanusz 8a6843aac1 Fix ApiChatCompletionRequest 2026-02-10 03:14:14 +01:00
Leszek Hanusz 8e125febc9 Don't use ChatService.notifyTimings 2026-02-10 01:54:05 +01:00
Leszek Hanusz a35e4c4d81 Use a separate callbacks argument for sendCompletion 2026-02-10 01:20:14 +01:00
Leszek Hanusz 8f79f1fccb Removing non-stream /completion implementation + fix api 2026-02-10 00:39:26 +01:00
손희준 820ebfa6f4
Server: log when converting requests to chat completions format (#19457) 
* Log converting requests

* Print as debug instead of info [no ci]

---------

Co-authored-by: openingnow <>
 2026-02-09 16:22:57 +01:00
Sascha Rogmann 292f6908cd
spec : remove check rate (#19377) 
* spec: remove parameter spec-ngram-check-rate

* spec : renamed statistics vars

* spec : add n_call_begin, n_call_accept

* spec : don't enable key-map-stats
 2026-02-09 15:30:50 +02:00
Georgi Gerganov eb449cdfa4
server : improve context checkpoint logic (#19408) 2026-02-08 09:40:04 +02:00
Georgi Gerganov dfde5993ea
common : add common_speculative_is_compat() (#19270) 
* llama : add llama_memory_can_rm_suffix()

* Revert "llama : add llama_memory_can_rm_suffix()"

This reverts commit d30e59b62a.

* spec : check if the target context is compatible for spec decoding
 2026-02-06 16:47:22 +02:00
Leszek Hanusz a0c5c26fb9 Fix calculation of total tokens after undo/redo 2026-02-05 02:33:39 +01:00
Leszek Hanusz 4659a36ffd Add 42px min height to the statistics to avoid flickering height problems + remove unused imports 2026-02-04 18:44:22 +01:00
Leszek Hanusz 77dc99cd9a Remove [DONE] check 2026-02-04 18:11:27 +01:00
Leszek Hanusz 031e426005 Run npm run format 2026-02-04 16:31:44 +01:00
Leszek Hanusz 393faf0166 Put completion api service in separate file 2026-02-04 16:29:53 +01:00
Leszek Hanusz 251ba9d72a Put tokenize in a separate file 2026-02-04 15:58:54 +01:00
Leszek Hanusz efd274ab3d chore: update webui build output 2026-02-04 14:25:20 +01:00
Leszek Hanusz ad3b8df38f Remove currentConfig.model 2026-02-04 02:03:59 +01:00
Leszek Hanusz f20b17a087 Remove inputContent var and use tokenize only when needed 2026-02-04 01:23:24 +01:00
Leszek Hanusz 9cf4742adb Fix tokenize with router on 2026-02-04 00:21:56 +01:00
Leszek Hanusz 03077cf297 Merge branch 'master' into notebook 2026-02-03 03:04:31 +01:00
Leszek Hanusz 210dc6a2c0 Running npm run format 2026-02-03 02:27:10 +01:00
Leszek Hanusz 9dc75f2664 Fix npm run check errors 2026-02-03 02:22:32 +01:00
Leszek Hanusz f42d889a47 Fix vertical alignment of Generate tooltip shortcut info 2026-02-03 02:14:28 +01:00
Leszek Hanusz fb2095e815 Show total number of tokens by using tokenizer 2026-02-03 01:50:52 +01:00
Leszek Hanusz 3657a8a7ad Implement shortcuts for the notebook page 2026-02-02 23:59:36 +01:00
Leszek Hanusz 7892b259cb Add last undo/redo for notebook page 2026-02-02 22:39:07 +01:00
Leszek Hanusz f041a864ed Use same dialog for server errors on notebook page 2026-02-02 21:29:48 +01:00
Leszek Hanusz 11e3cd81ce Protect window from accidental closure if the notebook is not empty as it is not saved 2026-02-02 21:15:24 +01:00
Leszek Hanusz 301c3fec7e Add generation statistics to notebook page 2026-02-02 18:39:46 +01:00
Matthieu Coudron a3fa035822
server: print actual model name in 'model not found" error (#19117) 
Experimenting with AI, my environment gets messy fast and it's not
always easy to know what model my software is trying to load. This helps
with troubleshooting.

before:

Error: {
  code = 400,
  message = "model not found",
  type = "invalid_request_error"
}

After:

Error: {
  code = 400,
  message = "model 'toto' not found",
  type = "invalid_request_error"
}
 2026-02-02 16:55:27 +01:00
Leszek Hanusz 8a71126e5b Autoscroll the notebook textarea depending on config parameter 2026-02-02 16:19:53 +01:00
Leszek Hanusz e80ba11778 Fix sidebar behavior same as chat pages 2026-02-02 15:46:12 +01:00
Leszek Hanusz ff2f0bba4a Remove console logs 2026-02-02 15:06:51 +01:00
Christian Kastner 7a4ca3cbd9
docs : Minor cleanups (#19252) 
* Update old URLs to github.com/ggml-org/

* Bump copyrights
 2026-02-02 08:38:55 +02:00
Leszek Hanusz c9f9863268 Add .agent/ to gitignore 
Fix buttons
Fix model loading with router enabled
remove stats for now
lint
 2026-02-01 23:20:34 +01:00
Leszek Hanusz 3af9b34aa2 Refine Notebook UI: improved layout, added stats and model info 2026-01-31 23:59:45 +01:00
Leszek Hanusz 6d96745375 Implement Notebook interface 2026-01-31 22:14:28 +01:00
Georgi Gerganov bbada8bfb9
server : wrap around the "id_slot" parameter (#19207) 
* server : wrap around the "id_slot" parameter

* cont : minor
 2026-01-30 19:46:10 +02:00
Georgi Gerganov dabaa2e77a
spec : add ngram-mod (#19164) 
* spec : add ngram-mod

* cont : simplify + keep track of occupancy

* cont : cleanup

* cont : move initialization to common/speculative

* cont : cleanup

* cont : cleanup

* cont : fix
 2026-01-30 18:21:48 +02:00
Andrew Marshall 84b0a98319
webui: Update Svelte to fix effect_update_depth_exceeded errors (#19144) 
The upstream fix is first available in 5.38.2, so constrain to at least
that version.

Rebuild pre-compiled webui index.html.gz based on these changes.

See also:
https://github.com/ggml-org/llama.cpp/issues/16347
https://github.com/huntabyte/bits-ui/issues/1687
https://github.com/sveltejs/svelte/issues/16548
 2026-01-29 15:56:39 +01:00
Sascha Rogmann 72d3b1898a
spec : add self‑speculative decoding (no draft model required) + refactor (#18471) 
* server: introduce self-speculative decoding

* server: moved self-call into speculative.cpp

* can_speculate() includes self-speculation

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* server: can_speculate() tests self-spec

* server: replace can_speculate() with slot.can_speculate()

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* common: use %zu format specifier for size_t in logging

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* server: can_speculate() requires a task instance

* common: ngram map, config self-speculative decoding

* common: add enum common_speculative_type

* common: add vector of speculative states

* common: add option --spec-draftless

* server: cleanup (remove slot.batch_spec, rename)

* common: moved self-spec impl to ngram-map

* common: cleanup (use common_speculative_state_draft)

* spec : refactor

* cont : naming

* spec: remove --spec-config

* doc: (draftless) speculative decoding

* common: print performance in spec decoding

* minor : cleanup

* common : better names

* minor : cleanup + fix build

* minor: comments

* CODEOWNERS: add common/ngram-map.* (#18471)

* common : rename speculative.draftless_type -> speculative.type

* ngram-map : fix uninitialized values

* ngram-map : take into account the input can become shorter

* ngram-map : revert len check for now

* arg : change `--spec-draftless` -> `--spec-type`

* spec : add common_speculative_state::accept()

* spec : refactor + add common_speculative_begin()

* spec : fix begin() call with mtmd

* spec : additional refactor + remove common_speculative_params

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2026-01-28 19:42:42 +02:00