Concedo
0755f27372
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .devops/openvino.Dockerfile
# .github/workflows/build-self-hosted.yml
# .github/workflows/build.yml
# common/chat.cpp
# docs/backend/OPENVINO.md
# examples/speculative-simple/speculative-simple.cpp
# ggml/src/ggml-hexagon/ggml-hexagon.cpp
# ggml/src/ggml-hexagon/htp/CMakeLists.txt
# ggml/src/ggml-hexagon/htp/htp-ctx.h
# ggml/src/ggml-hexagon/htp/htp-ops.h
# ggml/src/ggml-hexagon/htp/main.c
# ggml/src/ggml-hexagon/libggml-htp.inf
# ggml/src/ggml-openvino/ggml-decoder.cpp
# ggml/src/ggml-openvino/ggml-openvino-extra.cpp
# ggml/src/ggml-openvino/ggml-openvino.cpp
# ggml/src/ggml-openvino/ggml-quants.cpp
# ggml/src/ggml-openvino/openvino/op/rope.cpp
# ggml/src/ggml-openvino/openvino/op_table.cpp
# ggml/src/ggml-openvino/openvino/op_table.h
# ggml/src/ggml-openvino/openvino/translate_session.cpp
# ggml/src/ggml-openvino/openvino/utils.cpp
# ggml/src/ggml-openvino/openvino/utils.h
# ggml/src/ggml-openvino/utils.cpp
# ggml/src/ggml-openvino/utils.h
# ggml/src/ggml-sycl/common.hpp
# ggml/src/ggml-sycl/convert.cpp
# ggml/src/ggml-sycl/convert.hpp
# ggml/src/ggml-sycl/gemm.hpp
# ggml/src/ggml-sycl/ggml-sycl.cpp
# ggml/src/ggml-sycl/set_rows.cpp
# ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
# ggml/src/ggml-webgpu/ggml-webgpu.cpp
# scripts/sync_vendor.py
# tests/CMakeLists.txt
# tests/test-chat.cpp
# tools/cli/cli.cpp
# tools/mtmd/CMakeLists.txt
# tools/server/CMakeLists.txt
2026-04-23 00:55:05 +08:00
Concedo
becf70d49b
fixed logspam for fit
2026-04-23 00:43:09 +08:00
Concedo
96ec87127a
updated colab, handle connection dropping during prompt processing
2026-04-21 21:46:13 +08:00
Concedo
4629b49afb
updated to handle changes for clip_is_mrope
2026-04-21 19:34:32 +08:00
Concedo
19a12bb080
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# CODEOWNERS
# common/CMakeLists.txt
# ggml/CMakeLists.txt
# 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/mul_mat_vec.wgsl
# scripts/sync-ggml.last
# tools/cli/cli.cpp
# tools/llama-bench/llama-bench.cpp
# tools/perplexity/perplexity.cpp
2026-04-21 18:53:03 +08:00
Concedo
1feba4e4ea
fixed koboldcpp.sh, fixed vision max/min when one param is missing, fixed processing count wrong, updated lite
2026-04-21 18:36:47 +08:00
Concedo
71b4107bb6
fixed terminal logs
2026-04-19 11:31:12 +08:00
Concedo
e5eab545f3
handle override jinja template
2026-04-19 00:30:28 +08:00
Concedo
17c754a5fc
improved reasoning budget
2026-04-18 17:19:09 +08:00
Concedo
0b37cb9a57
added preliminary support for reasoning budget
2026-04-18 11:56:33 +08:00
Concedo
9a38091207
support q5_1 kv
2026-04-17 17:06:15 +08:00
Concedo
cccb45a00a
summary outputs include processed amt
2026-04-17 14:22:51 +08:00
Concedo
64ce5fca15
better approach when SWA window exceeded, simply refill the window. this is not 100% correct but good enough for fastforward users. Disable FF or increase window if not good enough
2026-04-17 11:44:13 +08:00
Concedo
b5e317e015
SWA fix attempt 2
2026-04-17 00:33:45 +08:00
Concedo
ae292c496e
handle SWA conflicting with rewind, increased default SWA padding.
2026-04-16 17:00:26 +08:00
Concedo
0251c6dbde
added swa padding controls
2026-04-16 16:21:48 +08:00
Concedo
535df844dd
touchup for min/max tokens ui
2026-04-16 14:56:22 +08:00
Llama
c592bd01da
Pass img_min_params and img_max_params to ctx_clip_params ( #2133 )
...
* Pass img_min_params and img_max_params to ctx_clip_params
These values determine the minimum and maximum size (in
tokens) of vision embeddings. The default value of -1
uses a model-dependent default size, for example for
Gemma 4 the default is a 280 token embedding. For higher
quality results (at the cost of using more memory and
slower speed) you can increase the size of the embedding
to 1120 tokens.
* Change dict to mydict to match change to method
2026-04-16 12:27:06 +08:00
Concedo
9c0b9b0bb1
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# docs/development/HOWTO-add-model.md
# docs/multimodal.md
# ggml/src/ggml-sycl/convert.cpp
# ggml/src/ggml-sycl/dequantize.hpp
# ggml/src/ggml-sycl/element_wise.cpp
# ggml/src/ggml-sycl/gated_delta_net.cpp
# ggml/src/ggml-sycl/ggml-sycl.cpp
# ggml/src/ggml-sycl/upscale.cpp
# ggml/src/ggml-webgpu/ggml-webgpu.cpp
# tests/test-backend-ops.cpp
# tests/test-llama-archs.cpp
# tools/mtmd/CMakeLists.txt
2026-04-14 20:06:04 +08:00
Concedo
ae60ea0009
handle updated gemma templates
2026-04-14 00:29:58 +08:00
Concedo
5361b45fba
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# ggml/src/ggml-opencl/CMakeLists.txt
# ggml/src/ggml-opencl/ggml-opencl.cpp
# ggml/src/ggml-opencl/kernels/cvt.cl
# requirements/requirements-tool_bench.txt
2026-04-12 16:22:26 +08:00
Concedo
919a010ebc
support outro but don't actually use it yet
2026-04-10 23:18:30 +08:00
Concedo
a1fc912452
try don't trigger the magic if input is following the jinja template.exactly for thinking models (+1 squashed commits)
...
Squashed commits:
[5542e81dc] try don't trigger the magic if input is following the jinja template.
2026-04-07 21:47:38 +08:00
Concedo
2d3fe0c113
revert my tweak, switch back to henk's original implementation for now, we can explore this again next time.
2026-04-07 19:00:58 +08:00
Concedo
e991bc044e
updated lite, modify henk fix to allow triggering on missing close only
2026-04-06 23:41:45 +08:00
Concedo
82cc19e055
calculate some fields before autofit for more accurate estimate
2026-04-06 20:44:37 +08:00
Concedo
f6e712d919
universal gemma4 fix, add memory check
2026-04-06 19:20:44 +08:00
henk717
4e30294cb1
Henk's Gemma4 31B Magic ( #2096 )
2026-04-06 18:49:19 +08:00
Concedo
6c937c05d9
improve ncmoe / moecpu regex
2026-04-04 23:53:13 +08:00
Concedo
db8bc40731
add some warnings if shifting fails
2026-04-04 23:16:26 +08:00
Concedo
eb3422996a
BOS fix for gemma4
2026-04-04 22:15:01 +08:00
Concedo
97f785efce
ensure BOS on vision prefix
2026-04-03 16:20:36 +08:00
Concedo
e8cffa37c8
fixed gemma4v image crashing on encode, however images are not yet working correctly
2026-04-03 15:56:35 +08:00
Concedo
0c2b679ea3
support bf16 quantkv cache type
2026-03-28 00:01:17 +08:00
Concedo
c91f350ed5
increase max images, take images from the end instead of beginning if too many images
2026-03-26 23:03:52 +08:00
Concedo
993925ba96
gracefully handle bad grammar instead of crashing
2026-03-23 17:00:53 +08:00
Concedo
07327b6c10
double n_batch size when pipeline parallel is enabled, keep u_batch the same
2026-03-21 11:22:10 +08:00
Concedo
3113e3a643
move main device print
2026-03-21 10:47:21 +08:00
Concedo
f579939057
updated lite, change smartcache snapshot behavior to conserve slots
2026-03-15 15:15:39 +08:00
Concedo
fcdf2f40d5
no need snapshot after gen is complete.
2026-03-15 12:34:48 +08:00
Concedo
33211e6edf
timing measure fixes
2026-03-15 12:23:14 +08:00
Concedo
500a1ab466
disable smartcache if slots is zero
2026-03-10 08:57:31 +08:00
Concedo
0df18d2ae2
fixed single token bans
2026-03-07 22:50:53 +08:00
JustCommitRandomness
2fbc3b2ae5
Adjust int types in format strings ( #2009 )
...
* tweak format sting types
This may not be all of them, but it's the ones which warn on OpenBSD
* complete the changes needed to fix the format string specifers
* avoid using inttypes, directly cast to size_t (u64 usually) instead
---------
Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com>
2026-03-06 19:06:18 +08:00
Concedo
e36d7b6464
warn about RNN models not supporting antislop
2026-03-06 14:02:51 +08:00
Concedo
4f1b22c415
kv snapshots save and load last logits for correctness. added some text for musicui, updated docs
2026-03-04 21:57:28 +08:00
Concedo
54cf43ae64
rnn fix adjust
2026-03-04 10:59:51 +08:00
Concedo
707f7b37bf
optimize pp
2026-03-03 21:02:51 +08:00
Concedo
ae67caa2f7
ace qwen rep pen for codes
2026-03-02 21:18:06 +08:00
Concedo
d904b51b0f
adjust slot counts
2026-03-02 15:56:15 +08:00