4479c382ce
demo: type inferrence
2025-12-30 17:26:23 +01:00
9c0fa6f810
rm workarounds
2025-12-30 16:07:23 +01:00
9e9a70f72f
more fixes
2025-12-29 15:07:18 +01:00
026730e8e3
more fix, more tests
2025-12-29 12:53:31 +01:00
1cf25734a9
more tests
2025-12-29 10:53:32 +01:00
2a31c9a30c
a lot of fixes
2025-12-29 00:38:29 +01:00
1784a57e7b
impl global_from_json
2025-12-28 23:15:48 +01:00
55fe96a9df
add jinja-value.cpp
2025-12-28 22:49:31 +01:00
c7f246e7a5
allow func to access ctx
2025-12-28 22:15:10 +01:00
adad34f64d
add filter_statement
2025-12-28 22:02:22 +01:00
9a8a45ff3b
mostly works
2025-12-28 21:32:55 +01:00
45df0c91e7
testing more templates
2025-12-28 19:50:09 +01:00
db09a7468d
fix negate test
2025-12-28 19:07:01 +01:00
acb0effa25
allow print source on exception
2025-12-28 18:45:41 +01:00
64e29a5848
add mk_stmt
2025-12-28 17:48:14 +01:00
7f17608ea4
use shared_ptr for values
2025-12-28 17:46:25 +01:00
4331e9c8e9
keyword arguments and slicing array
2025-12-28 17:23:29 +01:00
45c194622e
support binded functions
2025-12-28 15:33:14 +01:00
4ca114b095
track input string even after transformations
2025-12-28 12:48:35 +01:00
81310d29c1
render gemma tmpl ok
2025-12-28 12:04:23 +01:00
10835f2720
eval with is_user_input
2025-12-27 23:25:20 +01:00
c08f4ddf01
use mk_val
2025-12-27 22:28:54 +01:00
da7bbe5813
wip
2025-12-27 22:25:19 +01:00
7ed11f78f9
add more builtins
2025-12-27 22:10:45 +01:00
15b3dbab05
add string builtins
2025-12-27 21:52:50 +01:00
5a041e65b8
fix map object
2025-12-27 20:38:06 +01:00
d8ef00e610
bin ops works!
2025-12-27 20:16:46 +01:00
8d1e9a0d12
shadow naming
2025-12-27 16:06:23 +01:00
7ad6eb39ca
binary_expression::execute
2025-12-27 16:00:07 +01:00
8cea1ed6b0
parser ok
2025-12-27 12:55:01 +01:00
7ac8e98b28
clean up
2025-12-27 12:35:19 +01:00
a6e0ae7a85
demo
2025-12-27 12:22:34 +01:00
a35fcb00b5
add vm types
2025-12-27 12:12:07 +01:00
15b7c50e95
lexer
2025-12-25 21:08:51 +01:00
8d8030142e
jinja vm
2025-12-25 00:19:23 +01:00
4cbafad4f0
model: support MiMo-V2-Flash ( #18328 )
...
* mimov2: convert ok
* rename mimov2 --> mimo2
* fix conversion
* runnable not incorrect
* use sink
* add_sliding_window_pattern
* add swa and per-layer n_head_kv
* correct params
* somewhat working
* correct gating func
* nits
* mimo2: wire RMS eps + MoE bias + converter guards
* add co-author
Co-authored-by: Aaryan-Kapoor <Aaryan-Kapoor@users.noreply.github.com>
* use add_rope_freq_base_swa
---------
Co-authored-by: Aaryan Kapoor <aaryankapoor2006@gmail.com>
Co-authored-by: Aaryan-Kapoor <Aaryan-Kapoor@users.noreply.github.com>
2025-12-24 23:07:08 +01:00
c184284230
fit-params : fix race condition in fit-params output ( #18276 )
2025-12-24 15:57:38 +01:00
c8a2417d7b
CUDA: experimental native mxfp4 support for blackwell ( #17906 )
...
* CUDA: experimental native mxfp4 support for blackwell
* optimize load_tiles
* optimize quantize_mxfp4
* cleanup
* first pass review: formatting
* use interleaved layout for mma
* mmq: add assert for size
* use __nv_fp4x4_e2m1
* use iter_k as 512, cleanup
* Use 1200 as blackwell instead of 1000
* address review comments
* mmq: fix stride
* quantize.cu: use reference impl of e8m0 scale
* address review comments
* add 120f-virtual + minor fixes
---------
Co-authored-by: Aman Gupta <aman>
2025-12-24 22:28:26 +08:00
54132f1b1f
model : support for LlamaBidirectionalModel architecture ( #18220 )
...
* model: llama-embed-nemotron
* minor: python lint
* changed arch-name
* templated llm_build_llama to be used for both llama and llama-embed arch
2025-12-24 14:02:36 +01:00
2a9ea2020c
vulkan: fix command buffer corruption in ggml_backend_vk_event_wait ( #18302 )
2025-12-24 12:36:34 +01:00
ce7a6dc0fc
CANN : refactor ACL graph cache ( #17752 )
...
Move the graph property checking code into methods of LRU cache.
Signed-off-by: Wang Weixuan <wangweixvan@gmail.com>
2025-12-24 17:50:24 +08:00
1ce0126b18
docs: Fix typos in SYCL documentation ( #18269 )
2025-12-24 17:19:47 +08:00
7f459c98e7
vulkan: use fewer FA rows for small cache runs ( #18280 )
2025-12-24 08:59:14 +01:00
cf2ffc02bc
CANN: Uses yarn_ramp cache in ROPE ( #17725 )
2025-12-24 14:55:33 +08:00
10355dc7d0
common: add `LLAMA_ARG_OVERRIDE_TENSOR` env var for `-ot` arg ( #18267 )
2025-12-24 14:19:12 +08:00
5ee4e43f26
server: return_progress to also report 0% processing state ( #18305 )
2025-12-23 21:49:05 +01:00
5b6c9bc0f3
webui: apply webui_settings on first load ( #18223 )
...
* webui: apply webui_settings on first load
The webui_settings from /props were not applied on initial load
when default_generation_settings.params was null
Now syncs whenever serverProps is available, regardless of params,
works for both single-model and router modes
* chore: update webui build output
2025-12-23 15:48:03 +01:00
849d021104
server: fix crash with model not having BOS/EOS ( #18321 )
2025-12-23 14:39:36 +01:00
8e3ead6e4d
model-conversion : add device option to run-org-model.py ( #18318 )
...
* model-conversion : add device option to run-org-model.py
This commit refactors the `run-org-model.py` script to include a
`--device` argument, to allow users to specify the device on which to
run the model (e.g., cpu, cuda, mps, auto).
It also extracts a few common functions to prepare for future changes
where some code duplication will be removed which there currently
exists in embedding scripts.
The Makefile is also been updated to pass the device argument, for
example:
```console
(venv) $ make causal-verify-logits DEVICE=cpu
```
* fix error handling and remove parser reference
This commit fixes the error handling which previously referenced an
undefined 'parser' variable.
2025-12-23 14:07:25 +01:00
12ee1763a6
rpc : add check for rpc buffer type ( #18242 )
2025-12-23 11:56:49 +02:00
Xuan Son Nguyen
Aadeshveer Singh
Aman Gupta
Saba Fallah
Jeff Bolz
Wang Weixuan
Jesse Ikonen
Ruben Ortlam
TianHao324
ddh0
Pascal
Daniel Bevenius
Chris Rohlf