af9a76b6dc
feat: Implement lazy MCP client shutdown
2026-02-13 13:17:32 +01:00
c7870a3903
feat: Enhance tool call streaming UI and output format
2026-02-13 13:17:32 +01:00
fb5e464fe7
feat: Display and manage servers in ChatForm actions
2026-02-13 13:17:32 +01:00
dc7a3f33ba
feat: Integrate server management dialog into chat settings
2026-02-13 13:03:15 +01:00
0b13c95519
feat: Implement dedicated server management UI components
2026-02-13 13:03:15 +01:00
8df7e4a54f
refactor: Centralize health check logic in store
2026-02-13 13:03:15 +01:00
9a8cae462e
feat: Enhance server config with headers and schema normalization
2026-02-13 13:03:15 +01:00
bc2d879dea
feat: Add McpLogo Svelte component
2026-02-13 13:03:15 +01:00
42d52605d9
refactor: Consolidate UI CSS classes into shared module
2026-02-13 13:03:15 +01:00
6c95020b06
chore: update webui build output
2026-02-13 12:57:23 +01:00
62dbc9f654
feat: Raw LLM output switch per message
2026-02-13 12:57:23 +01:00
284425097b
refactor: Tool call handling
2026-02-13 12:57:03 +01:00
5beeb88a37
docs: Update high-level architecture diagrams for MCP integration
2026-02-13 12:55:42 +01:00
acdd30e3af
feat: Add AgenticContent component for enhanced tool call rendering
2026-02-13 12:55:42 +01:00
49a8c8b148
refactor: Update ChatStore to leverage mcpStore for agentic flow
2026-02-13 12:55:42 +01:00
5b582beb75
feat: Implement agentic orchestration within ChatService
2026-02-13 12:55:03 +01:00
391479edb2
feat: Introduce reactive mcpStore for client lifecycle management
2026-02-13 12:55:03 +01:00
7e184c174d
feat: Refactor MCP client to use official SDK
2026-02-13 12:55:03 +01:00
1a041a5b9b
feat: Add @modelcontextprotocol/sdk and zod dependencies
2026-02-13 12:55:03 +01:00
2325d2a50d
refactor: Update Agentic and MCP config parsing to use new utils and constants
2026-02-13 12:55:03 +01:00
0c24db3178
feat: Centralize MCP and Agentic type definitions and constants
2026-02-13 12:55:02 +01:00
26a19183b7
feat: Introduce common utility functions
2026-02-13 12:55:02 +01:00
14f6728ef1
webui: use normalizedMessages after upstream refactor
2026-02-13 12:55:02 +01:00
cb99ed9f71
webui: MCP client with low coupling to current codebase
2026-02-13 12:55:02 +01:00
b2ecc0cdb4
support --verbose-prompt ( #19576 )
2026-02-13 12:49:10 +01:00
5065da554e
CUDA: loop over ne2*ne3 in case it overflows ( #19538 )
...
* CUDA: loop over ne2*ne3 in case it overflows
* use fastdiv
2026-02-13 17:01:40 +05:30
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
43919b7f4f
CUDA: Do not mutate cgraph for fused ADDs ( #19566 )
...
* Do not mutate cgraph for fused ADDs
1. We should try to minimize in-place changes to the incoming
ggml_cgraph where possible (those should happen in graph_optimize)
2. Modifying in-place leads to an additional, unnecessary graph capture
step as we store the properties before modifying the graph in-place
in the cuda-backend
* Assert ggml_tensor is trivially copyable
* Update ggml/src/ggml-cuda/ggml-cuda.cu
Co-authored-by: Aman Gupta <amangupta052@gmail.com>
---------
Co-authored-by: Aman Gupta <amangupta052@gmail.com>
2026-02-13 15:07:55 +05:30
423cf0b26f
docs : fix broken link and typo ( #19560 )
2026-02-13 09:38:09 +01:00
33a56f90a6
model : Kimi Linear fix conv state update ( #19531 )
...
* fix conv state update for llama-server parallel serving
---------
Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>
2026-02-13 09:10:18 +01:00
25224c8021
llama : remove deprecated codecvt ( #19565 )
...
Using the same conversion function ensures a consistent matching between
the regex pattern and the text.
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
2026-02-13 06:43:53 +01:00
2f5d8f8edc
vendor : update BoringSSL to 0.20260211.0 ( #19562 )
...
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
2026-02-13 06:43:26 +01:00
bb96bfd361
memory : fix kv cache size for hybrid models ( #19559 )
2026-02-13 07:36:24 +02:00
0644baefde
metal : improve concurrency ( #19555 )
2026-02-13 07:35:57 +02:00
490eb96b88
metal : support GGML_OP_SET ( #19548 )
2026-02-13 07:34:52 +02:00
3bb78133ab
hexagon: fix typo in vtcm_needs_release ( #19545 )
2026-02-12 15:07:49 -08:00
79cc0f2daf
opencl: add basic support for q4_1 ( #19534 )
...
* opencl: add q4_1 mv
* opencl: clean up
* opencl: add flattened q4_1 mv
* opencl: clean up
* opencl: add basic q4_1 mm
* opencl: fix whitespace
* opencl: add general q4_0 mm
2026-02-12 14:52:37 -08:00
338085c69e
args : add -kvu to llama-parallel ( #19577 )
2026-02-12 21:52:41 +02:00
4c61875bf8
webui: Add switcher to Chat Message UI to show raw LLM output ( #19571 )
2026-02-12 19:55:51 +01:00
4b385bfcf8
vendor : update cpp-httplib ( #19537 )
...
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
2026-02-12 16:11:22 +01:00
f488429380
llama : update outdated comment in llama.h ( #19428 )
...
* Updated documentation
Model is no longer a parameter
* llama : fix trailing whitespace in comment
---------
Co-authored-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2026-02-12 15:52:57 +01:00
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
ff599039a9
scripts : add support for forks in pr2wt.sh ( #19540 )
...
This commit adds support for using the pr2wt.sh (pull request to
workspace) script with forks of upstream llama.cpp.
2026-02-12 13:14:28 +01:00
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
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
3b3a948134
metal : update sum_rows kernel to support float4 ( #19524 )
2026-02-12 11:35:28 +02:00
6845f7f87f
Add a workaround for compilation with ROCWMMA_FATTN and gfx9 ( #19461 )
...
There is an upstream problem [1] with AMD's LLVM 22 fork and
rocWMMA 2.2.0 causing compilation issues on devices without
native fp16 support (CDNA devices).
The specialized types aren't resolved properly:
```
/opt/rocm/include/rocwmma/internal/mfma_impl.hpp:2549:37: error: ambiguous partial specializations of 'amdgcn_mfma<__half, __half, __half, 16, 16, 16>'
2549 | using ARegsT = typename Impl::ARegsT;
```
Add a workaround to explicitly declare the types and cast when
compiling with HIP and ROCWMMA_FATTN [2]. When this is actually
fixed upstream some guards can be used to detect and wrap the
version that has the fix to only apply when necessary.
Link: https://github.com/ROCm/rocm-libraries/issues/4398 [1]
Link: https://github.com/ggml-org/llama.cpp/issues/19269 [2]
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2026-02-12 09:38:35 +01:00
fa16e517a3
server : fix typo in README.md for features list ( #19510 )
...
extra l for full
2026-02-12 08:56:25 +01:00
313493de53
docs : update path in snapdragon README.md ( #19533 )
...
paths changed so original example didn't work
2026-02-12 08:13:51 +01:00
b1ff83bbb0
hexagon: further optimization and tuning of matmul and dot kernels ( #19407 )
...
* ggml-hexagon: implement 2x2 matmul kernel
* hexmm: implement vec_dot_rx2x2 for Q8_0 and MXFP4
* hexagon: fix editor config failures
* hexagon: refactor matmul ops to use context struct and remove wrappers
Also implement vec_dot_f16 2x2
* hexagon: refactor dyn quantizers to use mmctx
* hexagon: remove mm fastdiv from op_ctx
* hexagon: refactor matmul entry point to reduce code duplication
---------
Co-authored-by: Trivikram Reddy <tamarnat@qti.qualcomm.com>
2026-02-11 23:04:27 -08:00
Aleksander Grygier
Pascal
Sigbjørn Skjæret
Aman Gupta
Oliver Simons
Pavan Shinde
ymcki
Adrien Gallouët
Georgi Gerganov
Shupei Fan
lhez
Christian Schmitz
Daniel Bevenius
Mario Limonciello
RichardScottOZ
TriDefender
Max Krasnyansky