40aaa8a403
mtmd : add support for Qwen2-Audio and SeaLLM-Audio ( #13760 )
...
* mtmd : add Qwen2-Audio support
* small clean up
* update discussion link
* clarify mtmd_get_output_embd
* clarification in multimodal.md
* fix ultravox bug
* ggml_cont
2025-05-25 14:06:32 +02:00
d785f9c1fd
server: fix/test add_generation_prompt ( #13770 )
...
Co-authored-by: ochafik <ochafik@google.com >
2025-05-25 10:45:49 +01:00
f5cd27b71d
server: streaming of tool calls and thoughts when --jinja is on (#12379 )
...
* add common_json w/ support for truncated json healing
* add common_chat_msg_diff
* partial common_chat_parse
* refactor parser w/ optionals
* server: wire chat diffs in stream mode
* fix trigger of thinking models (must happen after thoughts are closed)
* fix functionary v3.2 raw python!
* rename: common_chat_syntax (now contains format)
* rm common_regex.at_start
* don't return empty <think></think>
* accommodate yet another deepseek r1 distill fantasy syntax (`<｜tool▁calls｜>`)
* fix QwQ 32B tool call parsing after thoughts (hermes2)
* better logs for grammar triggers
* consume spaces after parse_json_tool_calls
* fix required tool calls w/ thinking models that have pre-opened thinking tags
* fix thinking model's initial trigger + test qwq's template
* run most test_tool_call tests in stream + non-stream modes
* make functionary v3.2 parsing more strict (differentiate first match from others)
* send final diff from server, to close off raw python arguments
* support partial content streaming in Generic mode
* tool-call: allow content prelude before hermes2 tool calls (for Qwen2.5)
* Update function-calling.md
* Update tool_bench.py
* chat-parser: remove input from exception (llm output may contain PII)
---------
Co-authored-by: ochafik <ochafik@google.com >
Co-authored-by: Olivier Chafik <ochafik@users.noreply.github.com >
2025-05-25 01:48:08 +01:00
9ecf3e66a3
server : support audio input ( #13714 )
...
* server : support audio input
* add audio support on webui
2025-05-23 11:03:47 +02:00
8a1d206f1d
tts : fix n_ubatch + make WavTokenizer cache-less ( #13713 )
...
ggml-ci
2025-05-22 22:21:07 +03:00
797990c4bc
mtmd : add ultravox audio input ( #13623 )
...
* convert ok, load ok
* warmup ok
* test
* still does not work?
* fix padding
* temporary give up
* fix merge conflict
* build_ultravox()
* rm test
* fix merge conflict
* add necessary mtmd APIs
* first working version (only 4s of audio)
* will this monster compile?
* fix compile
* please compile
* fPIC
* fix windows
* various fixes
* clean up audio_helpers
* fix conversion
* add some debug stuff
* long audio input ok
* adapt the api
* add --audio arg
* final touch UX
* add miniaudio to readme
* fix typo
* refactor kv metadata
* mtmd_default_marker()
2025-05-22 20:42:48 +02:00
cc74d5be99
server : pad small embedding batches ( #13692 )
...
ggml-ci
2025-05-22 16:33:39 +03:00
5fbfe384d4
server : improve error reporting ( #13680 )
2025-05-21 19:46:56 +03:00
0d5c742161
server : Add the endpoints /api/tags and /api/chat ( #13659 )
...
* Add the endpoints /api/tags and /api/chat
Add the endpoints /api/tags and /api/chat, and improved the model metadata response
* Remove trailing whitespaces
* Removed code that is not needed for copilot to work.
2025-05-21 15:15:27 +02:00
42158ae2e8
server : fix first message identification ( #13634 )
...
* server : fix first message identification
When using the OpenAI SDK (https://github.com/openai/openai-node/blob/master/src/lib/ChatCompletionStream.ts#L623-L626 ) we noticed that the expected assistant role is missing in the first streaming message. Fix this by correctly checking for the first message.
Co-authored-by: Piotr Stankiewicz <piotr.stankiewicz@docker.com >
Signed-off-by: Dorin Geman <dorin.geman@docker.com >
* server : Fix checks for first role message for stream=True
Co-authored-by: Piotr Stankiewicz <piotr.stankiewicz@docker.com >
Signed-off-by: Dorin Geman <dorin.geman@docker.com >
---------
Signed-off-by: Dorin Geman <dorin.geman@docker.com >
Co-authored-by: Piotr Stankiewicz <piotr.stankiewicz@docker.com >
2025-05-21 15:07:57 +02:00
797f2ac062
kv-cache : simplify the interface ( #13660 )
...
* kv-cache : simplify the interface
ggml-ci
* context : revert llama_batch_allocr position change
ggml-ci
2025-05-21 15:11:13 +03:00
b7a17463ec
mtmd-helper : bug fix to token batching in mtmd ( #13650 )
...
* Update mtmd-helper.cpp
* Update tools/mtmd/mtmd-helper.cpp
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com >
---------
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com >
2025-05-20 18:55:30 +02:00
e298d2fbd0
kv-cache : add SWA support ( #13194 )
...
* kv-cache : prepare for SWA
ggml-ci
* kv-cache : initial iSWA implementation
ggml-ci
* kv-cache : rework error recovery logic
ggml-ci
* models : fix Phi-3 SWA parameters
ggml-ci
* model : adjust Granite to rope factor changes
ggml-ci
* server : check if context can do shifts
ggml-ci
* iswa : for now, always enable shifts (experiment)
ggml-ci
* kv-cache : simplify SWA logic
ggml-ci
* kv-cache : apply defrag when we fail to find slots for the batch
ggml-ci
* llama : update docs about llama_decode
ggml-ci
* kv-cache : update warning logs when no space for the batch is available
ggml-ci
* llama : add llama_kv_self_seq_pos_min()
* kv-cache : keep track of partial SWA computes and print warnings
* server : disallow use cases involving partial SWA context
ggml-ci
* llama : add param to control SWA cache size
ggml-ci
* minor : clean-up
ggml-ci
2025-05-20 08:05:46 +03:00
f7c9429c85
sycl : Overcoming workaround for mmap() allocation on Windows ( #13482 )
...
* Remove mmap workaround on windows
After some testing I found that mmap is supported on windows and for
many GPUs on Linux. Therefore I remove the workaround for windows since
it is not necessary.
* Update llama-bench README
SYCL backend introduced a workaround that allows execution of
llama-bench also without specifying `--mmp 0` flag
2025-05-20 08:54:43 +08:00
92ecdcc06a
mtmd : add vision support for llama 4 ( #13282 )
...
* wip llama 4 conversion
* rm redundant __init__
* fix conversion
* fix conversion
* test impl
* try this
* reshape patch_embeddings_0
* fix view
* rm ffn_post_norm
* cgraph ok
* f32 for pos embd
* add image marker tokens
* Llama4UnfoldConvolution
* correct pixel shuffle
* fix merge conflicts
* correct
* add debug_graph
* logits matched, but it still preceives the image incorrectly
* fix style
* add image_grid_pinpoints
* handle llama 4 preprocessing
* rm load_image_size
* rm unused line
* fix
* small fix 2
* add test & docs
* fix llava-1.6 test
* test: add notion of huge models
* add comment
* add warn about degraded quality
2025-05-19 13:04:14 +02:00
6a2bc8bfb7
server : added --no-prefill-assistant flag ( #13608 )
...
* added no-prefill-assistant flag
* reworded documentation comment
* updated server README.md
2025-05-17 23:59:48 +02:00
6aa892ec2a
server : do not return error out of context (with ctx shift disabled) ( #13577 )
2025-05-16 21:50:00 +02:00
aea9f8b4e7
webui : improve accessibility for visually impaired people ( #13551 )
...
* webui : improve accessibility for visually impaired people
* add a11y for extra contents
* fix some labels being read twice
* add skip to main content
2025-05-16 21:49:01 +02:00
6c8b91500e
llama-bench : fix -ot with dl backends ( #13563 )
2025-05-15 15:46:55 +02:00
3cc1f1f1d2
webui : handle PDF input (as text or image) + convert pasted long content to file ( #13562 )
...
* webui : handle PDF input (as text or image)
* handle the case where pdf image + server without mtmd
* fix bug missing pages
2025-05-15 14:24:50 +02:00
c753d7bed0
server : proper error handling for missing elements in messages array (OpenAI compatible backend) ( #13540 )
2025-05-15 08:40:58 +02:00
b2838049cc
bench : handle decode errors ( #13548 )
...
ggml-ci
2025-05-15 05:57:02 +03:00
aa48e373f2
server: inject date_string in llama 3.x template + fix date for firefunction v2 (#12802 )
...
* Inject date_string in llama 3.x + fix for functionary v2
https://github.com/ggml-org/llama.cpp/issues/12729
* move/fix detection of functionary v3.1 before llama 3.x, fix & test their non-tool mode
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
* generate more tokens in test_completion_with_required_tool_tiny_fast to avoid truncation
---------
Co-authored-by: ochafik <ochafik@google.com >
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
2025-05-15 02:39:51 +01:00
3198405e98
common: add partial regex support (#12808 )
...
* move string_find_partial_stop & string_ends_with to common
* add common_regex (supports partial matches)
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* Update common/regex-partial.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* Update common/regex-partial.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* Update common/regex-partial.h
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* partial regex: add missing iterator end checks
* string utils: use string_views
* direct throw to avoid ggml.h include
* regex-partial: replace missed ggml_asserts
---------
Co-authored-by: ochafik <ochafik@google.com >
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2025-05-14 19:50:57 +01:00
053174436f
server : passthrough the /models endpoint during loading ( #13535 )
...
* server : passthrough the /models endpoint during loading
* server : update readme + return json for "meta" field
2025-05-14 15:42:10 +03:00
360a9c98e1
server : fix cache_tokens bug with no cache_prompt ( #13533 )
2025-05-14 13:35:07 +02:00
bb1681fbd5
webui : use fflate for more deterministic gzip compress ( #13525 )
...
* webui : use pako for more deterministic gzip compress
* simpler code
* use fflate instead of pako
2025-05-14 10:26:12 +02:00
d486dd3e8e
webui: Allow pasting file from clipboard ( #13526 )
...
* server: Allow pasting file from clipboard
* server: Prevent default action on file paste
* update build
* format then build combined
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co >
2025-05-14 10:07:31 +02:00
e5c834f718
quantize : improve tensor-type pattern matching ( #13033 )
2025-05-13 19:12:31 +02:00
71bdbdb587
clip : clip.h become private API ( ⚠️ breaking change) ( #13510 )
2025-05-13 17:07:21 +02:00
b89d605a91
batched-bench : fix pp batch contents ( #13492 )
2025-05-13 18:01:53 +03:00
b4726345ac
mtmd : remove libllava, remove clip-quantize-cli ( ⚠️ breaking change) ( #13460 )
...
* mtmd : remove libllava, remove clip-quantize-cli
* rm clip_model_quantize
2025-05-13 15:33:58 +02:00
cf0a43bb64
llama-bench : add defrag-thold, check for invalid ranges ( #13487 )
2025-05-13 00:31:37 +02:00
de4c07f937
clip : cap max image size 1024 for qwen vl model ( #13478 )
2025-05-12 15:06:51 +02:00
91159ee9df
server : allow content to be null in oaicompat_completion_params_parse ( #13477 )
2025-05-12 13:56:42 +02:00
22cdab343b
llama-bench : accept ranges for integer parameters ( #13410 )
2025-05-12 13:08:22 +02:00
c104023994
mtmd : Use RMS norm for InternVL 3 38B and 78B mmproj ( #13459 )
2025-05-12 00:39:06 +02:00
9a390c4829
tools : fix uninitialized llama_batch in server ( #13436 )
...
* add constructor to initialize server_context::batch, preventing destructor's call to llama_batch_free from causing an invalid free()
* Update tools/server/server.cpp
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com >
* use C++11 initializer syntax
* switch from Copy-list-initialization to Direct-list-initialization
---------
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com >
2025-05-11 17:08:26 +02:00
7f323a589f
Add --no-op-offload to improve -ot pp perf in MoE models like llama4 400B ( #13386 )
2025-05-11 14:18:39 +02:00
3eac209319
mtmd : support InternVL 3 38B and 78B mmproj ( #13443 )
...
* Support InternVL 3 38B and 78B mmproj
* Swap norms in clip.cpp
* Group variables together
2025-05-11 11:35:52 +02:00
a634d75d1b
mtmd : move helpers to dedicated file ( #13442 )
...
* mtmd : move helpers to dedicated file
* fix windows build
* rm redundant include
2025-05-11 11:34:23 +02:00
15e6125a39
mtmd : add hard limit on image resolution for qwen2vl / qwen2.5vl ( #13434 )
...
* mtmd : add hard limit on image resolution for qwen2vl / qwen2.5vl
* fix typo
2025-05-10 19:57:54 +02:00
3b24d26c22
server : update docs ( #13432 )
2025-05-10 18:44:49 +02:00
053367d149
mtmd : support InternVL 2.5 and 3 ( #13422 )
...
* convert : internvl support
* InternVL3-1B working
* fix regression
* rm mobilevlm from test
* fix conversion
* add test for internvl
* add to list of pre-quant
* restore boi/eoi check
* add clarify comment for norm eps
2025-05-10 16:26:42 +02:00
33eff40240
server : vision support via libmtmd ( #12898 )
...
* server : (experimental) vision support via libmtmd
* mtmd : add more api around mtmd_image_tokens
* mtmd : add more api around mtmd_image_tokens
* mtmd : ability to calc image hash
* shared_ptr for mtmd_image_tokens
* move hash to user-define ID (fixed)
* abstract out the batch management
* small fix
* refactor logic adding tokens to batch
* implement hashing image
* use FNV hash, now hash bitmap instead of file data
* allow decoding image embedding to be split into batches
* rm whitespace
* disable some features when mtmd is on
* fix --no-mmproj-offload
* mtmd_context_params no timings
* refactor server_inp to server_tokens
* fix the failing test case
* init
* wip
* working version
* add mtmd::bitmaps
* add test target
* rm redundant define
* test: mtmd_input_chunks_free
* rm outdated comment
* fix merging issue
* explicitly create mtmd::input_chunks
* mtmd_input_chunk_copy
* add clone()
* improve server_input struct
* clip : fix confused naming ffn_up and ffn_down
* rm ffn_i/o/g naming
* rename n_embd, n_ff
* small fix
* no check n_ff
* fix detokenize
* add const to various places
* add warning about breaking changes
* add c api
* helper: use mtmd_image_tokens_get_n_pos
* fix ctx_shift
* fix name shadowing
* more strict condition
* support remote image_url
* remote image_url log
* add CI test
* do not log base64
* add "has_multimodal" to /props
* remove dangling image
* speculative: use slot.cache_tokens.insert
* Apply suggestions from code review
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* rm can_be_detokenized
* on prmpt processing done, assert cache_tokens.size
* handle_completions_impl returns void
* adapt the new web ui
* update docs and hot topics
* rm assert
* small fix (2)
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2025-05-09 19:29:37 +02:00
27ebfcacba
llama : do not crash if there is no CPU backend ( #13395 )
...
* llama : do not crash if there is no CPU backend
* add checks to examples
2025-05-09 13:02:07 +02:00
efb8b47eda
imatrix : Add --parse-special for enabling parsing of special tokens in imatrix calculation ( #13389 )
...
* Add --parse-special for enabling parsing of special tokens in imatrix calculation
* whitespace
2025-05-09 11:53:58 +02:00
0527771dd8
llama-run: add support for downloading models from ModelScope ( #13370 )
...
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com >
2025-05-09 10:25:50 +01:00
2189fd3b63
mtmd : fix batch_view for m-rope ( #13397 )
...
* mtmd : fix batch_view for m-rope
* nits : fix comment
2025-05-09 11:18:02 +02:00
3f96aeff39
llama : one-off chat template fix for Mistral-Small-2503 ( #13398 )
...
* llama : one-off chat template fix for Mistral-Small-2503
* update readme
* add mistral-v7-tekken
2025-05-09 11:17:51 +02:00
