Concedo
9d38a9edc0
quick fix for colab
2026-05-17 00:18:02 +08:00
Concedo
0d320f60a6
fix multiuser regression
2026-05-17 00:17:12 +08:00
Concedo
47d5772fbe
add batching failure spam logs
2026-05-16 23:21:01 +08:00
Concedo
9203b6a051
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/labeler.yml
# .github/workflows/build-self-hosted.yml
# .github/workflows/release.yml
# .github/workflows/server-sanitize.yml
# .github/workflows/server-self-hosted.yml
# .github/workflows/server.yml
# .github/workflows/ui-build.yml
# .github/workflows/ui-ci.yml
# .github/workflows/ui-publish.yml
# .gitignore
# CMakeLists.txt
# CODEOWNERS
# scripts/ui-download.cmake
# scripts/xxd.cmake
# tests/test-backend-ops.cpp
# tests/test-reasoning-budget.cpp
# tools/CMakeLists.txt
# tools/server/CMakeLists.txt
# tools/server/README.md
2026-05-16 22:56:33 +08:00
Concedo
3095da076a
only fetch new popped horde requests if model is not blocked queue
2026-05-16 22:27:12 +08:00
Pascal
366c5e2a3b
ui: untrack settings sync in props effect to prevent reactive loop ( #23127 )
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Waiting to run
Python check requirements.txt / check-requirements (push) Waiting to run
Python Type-Check / python type-check (push) Waiting to run
2026-05-16 11:25:34 +02:00
Aleksander Grygier
1d9f99aa75
fix: Add build step using build workflow to publish workflow ( #23134 )
2026-05-16 11:22:59 +02:00
ynankani
42928bc14d
model : NvFP4 quantized LM head support ( #23046 )
...
* NvFP4 quantized LM head support
Signed-off-by: ynankani <ynankani@nvidia.com>
* Address review commnets
Signed-off-by: ynankani <ynankani@nvidia.com>
* Add assert for NvFp4 lm head and tied embeddings
Signed-off-by: ynankani <ynankani@nvidia.com>
* Address review commnets
Signed-off-by: ynankani <ynankani@nvidia.com>
* Create output_s tensor only when LM head NvFp4
Signed-off-by: ynankani <ynankani@nvidia.com>
---------
Signed-off-by: ynankani <ynankani@nvidia.com>
2026-05-16 11:09:27 +02:00
Concedo
80ce8a50b3
allow token bans and eos handling in
2026-05-16 15:20:46 +08:00
Wagner Bruna
f273fd35b9
sd: sync to master-601-eeac950 ( #2206 )
...
* sd: sync to master-601-eeac950
* sd: add mmap support
2026-05-16 11:23:10 +08:00
askmyteapot
3174fccb83
Fix linker error for kcpp_permit_any_repack ( #2210 )
...
Fixes `gpttype_adapter.lib(gpttype_adapter.obj) : error LNK2019: unresolved external symbol "int kcpp_permit_any_repack"`
It's a `bool`, not an `int`
2026-05-16 08:55:56 +08:00
Aleksander Grygier
59778f0196
ui: Restructure repo to use tools/ui folder and ui / UI / llama-ui / LLAMA_UI naming ( #23064 )
...
* webui: Move static build output from `tools/server/public` to `build/ui` directory
* refactor: Move to `tools/ui`
* refactor: rename CMake variables and preprocessor defines
- Rename LLAMA_BUILD_WEBUI -> LLAMA_BUILD_UI (old kept as deprecated)
- Rename LLAMA_USE_PREBUILT_WEBUI -> LLAMA_USE_PREBUILT_UI (old kept as deprecated)
- Backward compat: old vars auto-forward to new ones with DEPRECATION warning
- Rename internal vars: WEBUI_SOURCE -> UI_SOURCE, WEBUI_SOURCE_DIR -> UI_SOURCE_DIR, etc.
- Rename HF bucket: LLAMA_WEBUI_HF_BUCKET -> LLAMA_UI_HF_BUCKET
- Emit both LLAMA_BUILD_WEBUI and LLAMA_BUILD_UI preprocessor defines
- Emit both LLAMA_WEBUI_DEFAULT_ENABLED and LLAMA_UI_DEFAULT_ENABLED
* refactor: rename CLI flags (--webui -> --ui) with backward compat
- Add --ui/--no-ui (old --webui/--no-webui kept as deprecated aliases)
- Add --ui-config (old --webui-config kept as deprecated alias)
- Add --ui-config-file (old --webui-config-file kept as deprecated alias)
- Add --ui-mcp-proxy/--no-ui-mcp-proxy (old --webui-mcp-proxy kept as deprecated)
- Add new env vars: LLAMA_ARG_UI, LLAMA_ARG_UI_CONFIG, LLAMA_ARG_UI_CONFIG_FILE, LLAMA_ARG_UI_MCP_PROXY
- C++ struct fields: params.ui, params.ui_config_json, params.ui_mcp_proxy added alongside old fields
- Backward compat: old fields synced to new ones in g_params_to_internals
* refactor: update C++ server internals with backward compat
- Rename json_webui_settings -> json_ui_settings (both kept in server_context_meta)
- Rename params.webui usage -> params.ui (both synced, old still works)
- JSON API emits both "ui"/"ui_settings" and "webui"/"webui_settings" keys
- Server routes use params.ui_mcp_proxy || params.webui_mcp_proxy
- Preprocessor guards use #if defined(LLAMA_BUILD_UI) || defined(LLAMA_BUILD_WEBUI)
* refactor: rename CI/CD workflows, artifacts, and build script
- Rename webui-build.yml -> ui-build.yml; artifact webui-build -> ui-build
- Rename webui-publish.yml -> ui-publish.yml; var HF_BUCKET_WEBUI_STATIC_OUTPUT -> HF_BUCKET_UI_STATIC_OUTPUT
- Rename server-webui.yml -> server-ui.yml; job webui-build/checks -> ui-build/checks
- Update server.yml: job/artifact refs webui-build -> ui-build
- Update release.yml: all webui-build/publish refs -> ui-build/publish; HF_TOKEN_WEBUI_STATIC_OUTPUT -> HF_TOKEN_UI_STATIC_OUTPUT
- Update server-self-hosted.yml: webui-build -> ui-build
- Update build-self-hosted.yml: HF_WEBUI_VERSION -> HF_UI_VERSION
- Rename webui-download.cmake -> ui-download.cmake (internal refs updated)
- Update labeler.yml: server/webui -> server/ui path label
* docs: update CODEOWNERS and server README docs
- Update CODEOWNERS: team ggml-org/llama-webui -> ggml-org/llama-ui, path /tools/server/webui/ -> /tools/ui/
- Update server README.md: CLI tables show --ui flags with deprecated --webui aliases
- Update server README-dev.md: "WebUI" -> "UI", paths updated to tools/ui/
* fix: Small fixes for UI build
* fix: CMake.txt syntax
* chore: Formatting
* fix: `.editorconfig` for llama-ui
* chore: Formatting
* refactor: Use `APP_NAME` in Error route
* refactor: Cleanup
* refactor: Single migration service
* make llama-ui a linkable target
* fix: UI Build output
* fix: Missing change
* fix: separate llama-ui npm build output into build/tools/ui/dist subfolder + use cmake npm build instead of downloading ui-build.yml artifacts in CI
* refactor: UI workflows cleanup
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2026-05-16 02:02:40 +02:00
Sigbjørn Skjæret
49d1701bd2
ci : fix release symlinks ( #23119 )
2026-05-16 01:09:28 +02:00
Omer Ozarslan
1348f67c58
webui: Use lowercase hash for HF checksum check ( #23107 )
2026-05-15 19:38:16 +02:00
Pascal
cfabeb1bad
tests: add BF16 non-contig coverage for MUL_MAT permutations ( #22689 )
...
The MUL_MAT test loop iterates over base_types[] to generate non-contig
permutation cases (3 standard permutations across n in {1, 8, 16}).
BF16 is absent from base_types[], so these 9 cases were never generated
for BF16 even though every other type covered by base_types[] tests them.
Add the missing 9 cases explicitly: BF16 x F32, m=16, k=256, bs=[2,3],
permutations {0,2,1,3}, {0,1,3,2}, {0,3,2,1}, with n in {1, 8, 16}.
Suggested-by: @jeffbolznv
2026-05-15 19:35:05 +02:00
Julien Chaumond
6831fe470c
docs: document usage object in server timings response ( #23110 )
...
* docs: document `usage` object in server timings response
Co-Authored-By: julien-agent <Agents+cyolo@huggingface.co>
* Apply suggestion from @julien-c
---------
Co-authored-by: julien-agent <Agents+cyolo@huggingface.co>
2026-05-15 19:33:12 +02:00
Xuan-Son Nguyen
72e60f500d
mtmd: add chunks and fix preproc for qwen3a ( #23073 )
...
* mtmd: add chunks and fix preproc for qwen3a
* add attn_mask
* limit mtmd_chunk size (avoid blow up memory)
* correct audio tokens
* re-order the set_input case
* remove attn_mask
2026-05-15 19:32:47 +02:00
Pascal
8be1786707
webui: fix theme from --webui-config-file not applied on first load (fresh localStorage) ( #22902 )
2026-05-15 19:25:38 +02:00
Concedo
79666e5764
revert sdcpp build steps to use makefile and cmake without external txt files
2026-05-16 00:53:56 +08:00
Sigbjørn Skjæret
18d1717d62
convert : fix Qwen3 ASR conversion ( #23081 )
...
* fix qwen3asr
* fix qwen3asr
2026-05-15 18:38:39 +02:00
Concedo
77fa2cd348
batching horde worker adjustments
2026-05-16 00:30:23 +08:00
Concedo
f8391d527a
fix broken makefile
2026-05-15 23:02:38 +08:00
Concedo
74c6daba1a
fix bad merge
2026-05-15 22:47:24 +08:00
Piotr Wilkin (ilintar)
cc7200bf12
Refactor: convert_hf_to_gguf.py ( #17114 )
...
* move conversion code to a dedicated conversion directory and split the files akin to the src/models architecture
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2026-05-15 15:18:12 +02:00
Sigbjørn Skjæret
769cc93a43
ci : fix transform of top . entry in release archive ( #23080 )
...
* fix transform of top . entry in release archive
* simplify
2026-05-15 13:13:16 +02:00
Georgi Gerganov
d5dc2e0a02
llama-eval : add AIME 2026 dataset support ( #23058 )
...
Add Aime2026Dataset class loading from MathArena/aime_2026 on
HuggingFace. 30 problems (two sets of 15), single config/split.
Usage: --dataset aime2026
Assisted-by: llama.cpp:local pi
2026-05-15 13:58:30 +03:00
Aman Gupta
ac33f032ac
reasoning-budget: clone should do a deep-copy ( #23095 )
2026-05-15 11:59:07 +02:00
Concedo
35f524d3e2
horde advertise more threads when batching is enabled
2026-05-15 17:36:53 +08:00
Pascal
d528444580
webui: preserve partial response on streaming error ( #23090 )
2026-05-15 11:18:11 +02:00
Concedo
da2cc90723
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/labeler.yml
# .github/workflows/build-and-test-snapdragon.yml
# .github/workflows/build-self-hosted.yml
# .github/workflows/release.yml
# .github/workflows/server-self-hosted.yml
# .github/workflows/server-webui.yml
# .github/workflows/server.yml
# .gitignore
# CMakeLists.txt
# CONTRIBUTING.md
# README.md
# ggml/src/ggml-cuda/fattn.cu
# ggml/src/ggml-hexagon/htp/cpy-ops.c
# ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
# ggml/src/ggml-webgpu/ggml-webgpu.cpp
# grammars/README.md
# scripts/snapdragon/qdc/run_qdc_jobs.py
# scripts/snapdragon/qdc/tests/run_backend_ops_posix.py
# scripts/snapdragon/qdc/tests/run_bench_tests_posix.py
# scripts/snapdragon/qdc/tests/utils.py
# tests/test-backend-ops.cpp
# tests/test-chat.cpp
# tools/server/CMakeLists.txt
# tools/server/README.md
# tools/server/webui/src/lib/components/app/server/ServerLoadingSplash.svelte
# tools/server/webui/src/routes/(chat)/chat/[id]/+page.svelte
# ty.toml
2026-05-15 17:09:48 +08:00
Reithan
5962bca463
Fix jinja error on case-insensitive roles and 0-len messages result ( #2201 )
...
* fix jinja error on case-insensitive roles and 0-len messages result
* check length in correct place
2026-05-15 16:48:42 +08:00
Concedo
66a7b5e5de
prevent repacking if mmap is used, reduces memory footprint
2026-05-15 16:40:53 +08:00
Sid Shaytay
91e84fed64
Support for Codex CLI by skipping unsupported Responses tools ( #23041 )
...
Python Type-Check / python type-check (push) Waiting to run
* Support for Codex CLI by skipping unsupported Responses tools
* Warn on skipped Responses tools and preserve gpt-oss apply_patch rejection
* Revert gpt-oss apply_patch special handling
2026-05-15 09:03:24 +02:00
KITAITI Makoto
7155a49771
readme : update bindings ( #23063 )
2026-05-15 08:41:24 +03:00
Pranav Dhinakar
5c0e946837
ggml-hexagon: cpy: add contiguous fast-path in reshape copy ( #23076 )
2026-05-14 16:55:54 -07:00
Johannes Gäßler
3e037f313c
HIP: RDNA3 mma FA, faster AMD transpose, tune AMD ( #22880 )
...
Adds RDNA3 support to the CUDA mma FA kernel. To make the RDNA3 tensor cores work with the FP16 accumulation for VKQ the tiles they need to be 32 logical units long in direction of the attention head; for head sizes 80 and 112 that are not exactly divided by 32 the regular length of 16 with FP32 accumulation is used instead. The longer tiles also enable more efficient transposition for a warp size of 32 which is why it's also used for RDNA4. However, this scrambles the data layout of the accumulators along the attention head dimension. To prevent accidental misuse I added another entry to ggml_cuda_mma::data_layout.
I also tuned the kernel parameters for RDNA3, RDNA4, and CDNA1 in general, during which I discovered that the kernel can be made to work for head sizes up to 256 for CDNA. For RDNA3/4 I was not able to get better performance that the tile kernel for head sizes > 128.
2026-05-14 22:58:58 +02:00
Zack Li
d81e63dcfd
CI : support IOT device (IQ9) ( #22987 )
...
* update test scripts
* align CI behavior between linux and android
* remove automatically cancel in 15min
* enable cancel-in-progress
* fix ty check issue
* update and fix pylint issue
* update runner such that we are not restricted by the 15min limit rule
* fix flake8 lint issue
* update runner according to review feedback
* code update according to review feedback
* switch from llama-cli to llama-completion binary with -no-cnv flag
2026-05-14 13:58:34 -07:00
Reese Levine
834a243664
ggml-webgpu: Enable NVIDIA self-hosted CI ( #22976 )
...
* Enabel nvidia ci for webgpu
* Address precision issues
* fix placement
* Relax more set_rows and div
* Try relaxing all f16
* formatting and naming
* Add comment explaining max_nmse_err logic
Added comment referencing pull request for clarification.
2026-05-14 09:41:32 -07:00
Zheyuan Chen
5ec717d125
ggml-webgpu: makes the flash attn vec path subgroup-aware ( #23040 )
...
* ggml-webgpu: makes the flash attn vec path compile and size its split/reduce work from the device’s reported subgroup range instead of assuming 32 subgroup size.
* ggml-webgpu: remove the extra max_wg_size >= max_subgroup_size guard. Remove hardcoded 32 when determine the value of reduce_wg_size and vec_nwg_cap
2026-05-14 09:31:36 -07:00
Aleksander Grygier
0c3e4fccca
fix: Propagate version tag to WebUI asset download in self-hosted CI ( #23051 )
...
* fix: Propagate version tag to WebUI asset download in self-hosted CI
* refactor: Apply suggestions from @CISC
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* fix: Skip npm build when Node.js is not installed
Avoid 'no such file or directory' errors on CI runners that lack
Node.js. Check if npm is available via find_program before attempting
npm install + npm run build. Falls back to HF Bucket download.
* fix: Use + separator for ASSETS list to fix Windows build
Replace fragile \; escaping with a + separator when passing the
WebUI asset list via -DASSETS to the download script. On Windows,
the \; escaping was not reliably preserved through the CMake build
system, causing all asset filenames to be concatenated into one
(e.g., 'index.html;bundle.js;bundle.css;loading.html' as a single
file), which broke the HF Bucket download and subsequent xxd.cmake
step.
+ is safe because it is not special in cmd.exe (unlike | which is a
pipe operator), not special in CMake's -D argument parser, and not
a valid Windows filename character. CMakeLists.txt joins assets
with + and webui-download.cmake splits them back via regex.
* fix: Validate HF_WEBUI_VERSION environment variable with regex
Add input validation for the HF_WEBUI_VERSION env var to prevent
CMake list separator or path-traversal issues in stamp filenames
and download URLs. Rejects non-conforming characters early.
* fix: Remove 'latest' fallback for HF_WEBUI_VERSION
When needs.determine-tag.outputs.tag_name is empty, let CMake's
default resolution handle it (empty -> git-based version lookup)
instead of falling back to 'latest'. This ensures the sentinel
stamp file is consistent with CMake's resolution logic.
* fix: Demote checksum verification failure to warning instead of hard gate
* fix: End line character
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2026-05-14 17:57:20 +02:00
Aman Gupta
97b658cee8
contributing: new contributors should not submit trivial fixes ( #23045 )
2026-05-14 23:55:24 +08:00
Concedo
1fe1a083cd
run multiple horde workers if used with batching.
2026-05-14 23:36:42 +08:00
Wagner Bruna
bfe9548fd5
sd: sync to master-596-90e87bc ( #2204 )
...
* sd: reuse source lists between make and cmake
* sd: sync to master-596-90e87bc
* Update source file path for sdtype_adapter.cpp
---------
Co-authored-by: LostRuins Concedo <39025047+LostRuins@users.noreply.github.com>
2026-05-14 23:14:33 +08:00
Aleksander Grygier
253ba110bc
webui: Move static build output from repo code to HF Bucket ( #22937 )
...
* ci: add workflow to publish webui to Hugging Face bucket
* ci: add webui release job to release workflow
* ci: test webui release job
* chore: Return to default minification strategy for build output files
* ci: extract webui build into separate workflow and job
* chore: Ignore webui static output + clean up references
* chore: Delete legacy webui static output
* chore: Ignore webui build static output
* fix: Workflow
* fix: Versioning naming
* chore: Update package name
* test: Test CI fix
* refactor: Naming
* server: implement webui build strategy with HF Bucket support
* chore: Remove test workflow
* chore: Use WebUI build workflow call in other workflows
* server: HF Buckets fallback for WebUI build
* refactor: App name variable
* refactor: Naming
* fix: Retrieve loading.html
* fix: workflow syntax
* fix: Rewrite malformed release.yml
* fix: Req param
* test: Re-add missing Playwright installation for CI tests
* refactor: Logic & security improvements
* refactor: Retrieve publishing jobs and DRY the workflows
* fix: Test workflow syntax
* fix: Upstream Release Tag for test workflow
* chore: Remove test workflow
* ci: Run WebUI jobs on `ubuntu-24.04-arm`
* refactor: Post-CR cleanup
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com>
* refactor: CI cleanup
* refactor: Cleanup
* test: Test workflow
* refactor: use LLAMA_BUILD_NUMBER instead of LLAMA_BUILD_TAG for HF Bucket webui downloads
* server: add fallback mechanism for HF Bucket webui downloads from latest directory
* fix: Incorrect argument order in file(SHA256) calls for checksum verification
* refactor: Use cmake script for handling the HF Bucket download on build time
* feat: support local npm build for WebUI assets
* refactor: add `HF_ENABLED` flag to control WebUI build/download provisioning
* refactor: Cleanup
* chore: Remove test workflow
* fix: remove s390x from release workflow
* fix: add webui-build dependency to ubuntu-22-rocm and windows-hip
* Revert "fix: remove s390x from release workflow"
This reverts commit debcfffa9bc1e3112eae41f2d29741b682e4eb19.
* fix: Release workflow file
* fix: Proper release tag used for HF Bucket upload
* fix: Remove duplicate steps in release workflow
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2026-05-14 13:21:41 +02:00
Concedo
cc82c3164e
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .devops/intel.Dockerfile
# .github/workflows/build-cross.yml
# .github/workflows/build-sycl.yml
# .github/workflows/build.yml
# .github/workflows/editorconfig.yml
# .github/workflows/release.yml
# cmake/riscv64-spacemit-linux-gnu-gcc.cmake
# docs/backend/OPENVINO.md
# docs/backend/SYCL.md
# docs/build-riscv64-spacemit.md
# docs/ops.md
# docs/ops/WebGPU.csv
# embd_res/ggml-vocab-qwen35.gguf
# embd_res/ggml-vocab-qwen35.gguf.inp
# embd_res/ggml-vocab-qwen35.gguf.out
# examples/model-conversion/Makefile
# ggml/CMakeLists.txt
# ggml/src/ggml-cpu/CMakeLists.txt
# ggml/src/ggml-hexagon/ggml-hexagon.cpp
# ggml/src/ggml-hexagon/htp/hmx-flash-attn-ops.c
# ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
# ggml/src/ggml-hexagon/htp/hmx-utils.h
# ggml/src/ggml-hexagon/htp/htp-ops.h
# ggml/src/ggml-hexagon/htp/hvx-utils.h
# ggml/src/ggml-hexagon/htp/main.c
# ggml/src/ggml-hexagon/htp/unary-ops.c
# ggml/src/ggml-opencl/CMakeLists.txt
# ggml/src/ggml-opencl/ggml-opencl.cpp
# ggml/src/ggml-opencl/kernels/cvt.cl
# ggml/src/ggml-sycl/CMakeLists.txt
# ggml/src/ggml-sycl/common.cpp
# ggml/src/ggml-sycl/common.hpp
# ggml/src/ggml-sycl/ggml-sycl.cpp
# ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
# ggml/src/ggml-webgpu/ggml-webgpu.cpp
# ggml/src/ggml-webgpu/wgsl-shaders/common_decls.tmpl
# ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_tile.wgsl
# ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_reduce.wgsl
# ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_split.wgsl
# ggml/src/ggml-webgpu/wgsl-shaders/get_rows.wgsl
# ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
# ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec_acc.tmpl
# ggml/src/ggml-webgpu/wgsl-shaders/unary.wgsl
# ggml/src/ggml-zendnn/CMakeLists.txt
# ggml/src/ggml-zendnn/ggml-zendnn.cpp
# scripts/snapdragon/adb/run-completion.sh
# tests/CMakeLists.txt
# tools/cli/README.md
# tools/completion/README.md
# tools/mtmd/clip-impl.h
# tools/mtmd/clip.cpp
# tools/mtmd/clip.h
# tools/server/README.md
2026-05-14 19:04:04 +08:00
Concedo
6e42e0ebb6
revert to use upstream fix
2026-05-14 18:56:57 +08:00
Georgi Gerganov
67b2b7f2f2
logs : reduce ( #23021 )
...
Python Type-Check / python type-check (push) Waiting to run
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Has been cancelled
Python check requirements.txt / check-requirements (push) Has been cancelled
Update Operations Documentation / update-ops-docs (push) Has been cancelled
* logs : reduce
* args : fix envs
* server : fix build
* common : print verbosity level at start
* server : clean-up logs
* server : print prompt processing timings + sampling params
* minor : whitespaces
2026-05-14 13:05:52 +03:00
alex-spacemit
81b0d882ae
ggml-cpu: Add IME2 Instruction Support for the SpacemiT Backend ( #22863 )
2026-05-14 17:39:30 +08:00
Neo Zhang
0f45f1a35c
docker : revert stable version of intel compute-runtime ( #22968 )
2026-05-14 11:30:40 +02:00
Kabir Potdar
42532afff4
unicode,test: add Qwen3.5 non-backtracking tokenizer handler and regr… ( #22110 )
...
* unicode,test: add Qwen3.5 non-backtracking tokenizer handler and regression tests
- Add unicode_regex_split_custom_qwen35() to [src/unicode.cpp](src/unicode.cpp), a non-backtracking handler for Qwen3.5's [\p{L}\p{M}]+ regex (letters + combining marks).
- Register the handler in the custom tokenizer dispatch table to prevent stack overflows on long inputs (fixes #21919 ).
- Add [models/ggml-vocab-qwen35.gguf](models/ggml-vocab-qwen35.gguf) (test vocab), [models/ggml-vocab-qwen35.gguf.inp](models/ggml-vocab-qwen35.gguf.inp) (test cases), and [models/ggml-vocab-qwen35.gguf.out](models/ggml-vocab-qwen35.gguf.out) (expected output) for regression testing.
- Update [tests/CMakeLists.txt](tests/CMakeLists.txt) to include the new test entry.
This mirrors the Qwen2 fix (commit 0d049d6Closes #21919 .
* fix: enhance regex handling for Qwen3.5 tokenizer to include accent marks
* cont : remove trailing whitespace
---------
Co-authored-by: Kabir <kabir@example.com>
Co-authored-by: Alde Rojas <hello@alde.dev>
2026-05-14 11:03:40 +02:00
