-
99c53d6558
webui: Add a "Continue" Action for Assistant Message (#16971)
Aleksander Grygier
2025-11-19 14:39:50 +01:00
-
07b0e7a5ac
convert : use self.block_count everywhere instead of reading hparams (#17359)
Sigbjørn Skjæret
2025-11-19 11:52:38 +01:00
-
fd7353d5eb
cuda: fix rope fusion for gemma3 (#17378)
Aman Gupta
2025-11-19 18:25:05 +08:00
-
6fd4f95367
Fix too relaxed check on CUDA "fast copy" (can_be_transposed) condition (#17332)
Piotr Wilkin (ilintar)
2025-11-19 10:36:33 +01:00
-
980b7cd17e
vulkan: force full subgroups for flash attention to fix intel subgroup crash (#17356)
Ruben Ortlam
2025-11-19 08:46:26 +01:00
-
c49daff5ba
ggml-cpu: Don't pass -mpowerpc64 when -mcpu already implies it (#17308)
Jeremy Rand
2025-11-19 06:19:00 +00:00
-
10e9780154
chat: fix int overflow, prevent size calculation in float/double (#17357)
Xuan-Son Nguyen
2025-11-18 19:11:53 +01:00
-
a045492088
vocab : call reserve() for building plamo-2-translate suffix (#17343)
Haiyue Wang
2025-11-19 01:58:22 +08:00
-
1920345c3b
common : Generalized XML-style tool-call parsing with streaming support (GLM 4.5/4.6 + MiniMax M2 + SeedOSS + Kimi-K2 + Qwen3-Coder + Apriel-1.5 + Xiaomi-MiMo) (#16932)
hksdpc255
2025-11-19 04:54:15 +11:00
-
561a3e2788
ci : change the openEuler-310p image to fix release (#17361)
jiahao su
2025-11-19 01:10:23 +08:00
-
f40a2e5f11
gitignore : be more specific about ignored stuff (#17354)
Georgi Gerganov
2025-11-18 16:44:53 +02:00
-
bc4064cfea
CANN: fix acl_tensor_ptr usage in ASCEND_310P ROPE (#17347)
Chenguang Li
2025-11-18 16:41:52 +08:00
-
97cb3fd5ae
fix: resolve undefined variable 'svr' compilation error (#17348)
o7si
2025-11-18 16:10:47 +08:00
-
ffa277a54c
CANN: Add openEuler-cann in build and release (#17192)
jiahao su
2025-11-18 16:08:55 +08:00
-
da95bf2a85
vulkan: support noncontig i32 copy (#17328)
Jeff Bolz
2025-11-18 00:41:24 -06:00
-
0de8878c96
server: split HTTP into its own interface (#17216)
Xuan-Son Nguyen
2025-11-17 22:05:44 +01:00
-
38e2c1b412
vulkan: add log RTE support to fix Nvidia CI (#17320)
Ruben Ortlam
2025-11-17 21:37:49 +01:00
-
cb44fc84e8
cmake : fix ARM feature verification (#17170)
Adrien Gallouët
2025-11-17 21:37:29 +01:00
-
cb623de3fc
ggml : add missing AVX512 feature checks (#17270)
Adrien Gallouët
2025-11-17 12:12:00 +01:00
-
7aaeedc098
metal : support I32 -> I32 copy (#17317)
Georgi Gerganov
2025-11-17 11:52:00 +02:00
-
3347e6d904
metal : faster argsort (#17315)
Georgi Gerganov
2025-11-17 11:51:48 +02:00
-
1a139644a8
metal : add cumsum (#17305)
Georgi Gerganov
2025-11-17 11:51:13 +02:00
-
2376b7758c
CANN: Use smart pointers to manage ACL objects (#17238)
hipudding
2025-11-17 08:43:59 +08:00
-
dbed61294a
vulkan: add LOG operation support for F32 and F16 (#17183)
Pavels Zaicenkovs
2025-11-16 22:50:09 +01:00
-
80deff3648
vulkan: fix MMQ quantize_y condition (#17301)
Ruben Ortlam
2025-11-16 19:38:17 +01:00
-
8b1c339bd2
ci : revert #16249 (#17303)
Eve
2025-11-16 18:09:17 +00:00
-
416e7c7f47
metal : remove obosolete asserts (#17295)
Georgi Gerganov
2025-11-16 09:50:26 +02:00
-
5b2093becc
server : handle context overflow during decode (#17267)
Georgi Gerganov
2025-11-16 09:23:37 +02:00
-
52e5d421f1
opencl: fix rms_norm_mul (#17250)
lhez
2025-11-15 17:40:14 -08:00
-
4db5641210
opencl: add kernel to handle mat mul in attention to improve encoding speed (#17181)
shaofeiqi
2025-11-15 17:33:10 -08:00
-
72bd7321a7
sycl : unify unary kernels with a generic implementation and enable wide operator support (#17213)
shani-f
2025-11-16 01:52:42 +02:00
-
22e1ce2f81
webui: Fix clickability around chat processing statistics UI (#17278)
Aleksander Grygier
2025-11-15 22:41:41 +01:00
-
1411d9275a
webui: add OAI-Compat Harmony tool-call streaming visualization and persistence in chat UI (#16618)
Pascal
2025-11-15 21:09:32 +01:00
-
662192e1dc
convert : remove unnecessary chat template patching (#17289)
Sigbjørn Skjæret
2025-11-15 20:58:59 +01:00
-
24dc769f1b
vulkan: Fuse mul_mat_id+add_id+mul and mul_mat+add+add. (#17287)
Jeff Bolz
2025-11-15 12:54:23 -06:00
-
4dca015b7e
vulkan: Replace 16-bit unpack8 calls to work around legacy Windows AMD driver bug (#17285)
Ruben Ortlam
2025-11-15 15:18:58 +01:00
-
9a8860cf5d
convert : use all parts in safetensors index (#17286)
Sigbjørn Skjæret
2025-11-15 14:12:39 +01:00
-
9d3ef4809f
convert : set expert gating func in base class (#17279)
Sigbjørn Skjæret
2025-11-15 14:06:24 +01:00
-
c7b7db0445
mtmd-cli: Avoid logging to stdout for model loading messages in mtmd-cli (#17277)
Ankur Verma
2025-11-15 03:41:16 -08:00
-
1568d13c2c
vulkan: implement ABS and NEG (#17245)
Giuseppe Scrivano
2025-11-15 12:00:29 +01:00
-
439342ea0b
vulkan: Use ggml_vk_tensor_subbuffer in mul_mat_vec(id) paths (#17244)
Jeff Bolz
2025-11-15 04:56:15 -06:00
-
234ae7d7bd
vulkan: skip all-negative-inf blocks in FA (#17186)
Jeff Bolz
2025-11-15 03:37:25 -06:00
-
38eaf32af1
vulkan: change graph_compute to be async and enable get_tensor_async (#17158)
Jeff Bolz
2025-11-15 02:06:41 -06:00
-
9b17d74ab7
mtmd: add mtmd_log_set (#17268)
Xuan-Son Nguyen
2025-11-14 15:56:19 +01:00
-
e1fcf8b09b
model : add AfmoeForCausalLM support (#16477)
Bartowski
2025-11-14 07:54:10 -05:00
-
6cd0cf72ce
fix : Dangling pointer for non-empty trigger words in lazy grammar construction (#17048)
Marek Hradil jr.
2025-11-14 13:35:26 +01:00
-
d396b43748
server : fix "can batch with" bug (#17263)
Georgi Gerganov
2025-11-14 14:03:45 +02:00
-
45c6ef7307
metal : support argsort for ne00 > 1024 (#17247)
Georgi Gerganov
2025-11-14 09:36:06 +02:00
-
2606b0adab
metal : make the FA extra sizes consistent (#17143)
Georgi Gerganov
2025-11-14 09:13:34 +02:00
-
307772fcda
readme : add RVV,ZVFH,ZFH,ZICBOP support for RISC-V (#17259)
ixgbe
2025-11-14 15:12:56 +08:00
-
f1bad23f88
Better UX for handling multiple attachments in WebUI (#17246)
Aleksander Grygier
2025-11-14 01:19:08 +01:00
-
becc4816dd
ggml-cpu: handle 3d tensors in repack mat_mul (#17241)
Alberto Cabrera Pérez
2025-11-13 20:53:00 +00:00
-
c4abcb2457
server: fixing naming conflict res_error (#17243)
Xuan-Son Nguyen
2025-11-13 20:53:47 +01:00
-
389ac78b26
ggml : add ops SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM (#17063)
Piotr Wilkin (ilintar)
2025-11-13 19:54:47 +01:00
-
a19bd6f7ce
vulkan: remove shell call from vulkan-shaders-gen tool, revert file check (#17219)
Ruben Ortlam
2025-11-13 14:51:21 +01:00
-
dd091e52f8
sched : fix reserve ignoring user tensor assignments (#17232)
Diego Devesa
2025-11-13 04:14:02 -08:00
-
1215dde7b0
ggml-cpu : add RISC-V vector intrinsic support for silu and cvar operations (#17227)
ixgbe
2025-11-13 20:13:32 +08:00
-
0cfb19166b
metal: accelerated conv2d (#17175)
bagheera
2025-11-13 05:32:44 -06:00
-
2776db6c81
Revert "ggml-cpu: handle 3d tensors in repack mat_mul (#17030)" (#17233)
Georgi Gerganov
2025-11-13 12:59:37 +02:00
-
879dec341a
ggml-cpu : use template for argsort (#17222)
Diego Devesa
2025-11-13 00:59:05 -08:00
-
97d5117217
CANN: Add cross_entropy_loss op support (#16886)
TecJesh
2025-11-13 09:39:51 +08:00
-
a90eb94ca9
CUDA: fuse rope + set_rows (#16884)
Aman Gupta
2025-11-13 08:50:01 +08:00
-
07751f8d44
update SYCL support OPs (#17208)
Neo Zhang Jianyu
2025-11-13 08:42:23 +08:00
-
ffb6f3d921
vocab : correct bounds check for UGM XCDA array access (#17215)
o7si
2025-11-13 06:41:02 +08:00
-
5d6838b74f
CUDA: static assert to prevent misuse of memcpy_1 (#17198)
Johannes Gäßler
2025-11-12 23:13:55 +01:00
-
92bb442ad9
docker : preserve .so symlinks for docker container builds (#17214)
Mike Abbott
2025-11-12 12:33:55 -07:00
-
374fe09cdd
ggml : use std::sort in ggml_argsort CPU implementation (#17211)
Georgi Gerganov
2025-11-12 20:43:38 +02:00
-
8e878f0cb4
Update packages + upgrade Storybook to v10 (#17201)
Aleksander Grygier
2025-11-12 19:01:48 +01:00
-
00c94083b3
server: (refactor) implement generator-based API for task results (#17174)
Xuan-Son Nguyen
2025-11-12 18:50:52 +01:00
-
017eceed61
ci: add check vendor job (#17179)
Xuan-Son Nguyen
2025-11-12 14:56:02 +01:00
-
ee8dd5c658
server: move res_error/res_ok to static function (#17167)
Xuan-Son Nguyen
2025-11-12 14:17:24 +01:00
-
1c398dc9ec
ggml-cpu: handle 3d tensors in repack mat_mul (#17030)
Alberto Cabrera Pérez
2025-11-12 12:52:19 +00:00
-
52cf111b31
cmake : cleanup (#17199)
Adrien Gallouët
2025-11-12 13:48:30 +01:00
-
78010a0d52
cmake : move OpenSSL linking to vendor/cpp-httplib (#17177)
Adrien Gallouët
2025-11-12 12:32:50 +01:00
-
655cddd174
CANN: Add L2_NORM op support (#16856)
TecJesh
2025-11-12 15:11:42 +08:00
-
5da7664960
[SYCL]fix ci crash about SSM_CONV (#17169)
Neo Zhang Jianyu
2025-11-12 14:44:29 +08:00
-
23a46ce972
CANN: GGML_CANN_ACL_GRAPH works only USE_ACL_GRAPH enabled (#16861)
Raul Torres
2025-11-12 06:37:52 +00:00
-
c273d75375
hexagon: various Op fixes (#17135)
Max Krasnyansky
2025-11-11 15:25:04 -08:00
-
7d019cff74
disable rms norm mul rope for chips with no fp16 rte (#17134)
Eve
2025-11-11 18:53:30 +00:00
-
3fe36c3238
ci: add Arm-hosted Graviton4 runner (#17021)
sudhiarm
2025-11-11 15:58:05 +00:00
-
1d45b4228f
vendor: split httplib to cpp/h files (#17150)
Xuan-Son Nguyen
2025-11-11 13:32:58 +01:00
-
ca4844062b
ggml-cpu : add RISC-V RVV (Zvfh) optimization for FP16 to FP32 conversion (#17161)
ixgbe
2025-11-11 19:41:51 +08:00
-
73460f6278
ggml-cpu: templateify ggml_compute_forward_rope_f32 and _f16 (#16805)
duduta
2025-11-11 13:33:24 +02:00
-
8c583242ad
kleidiai: add optimized per-channel kernels for Q8_0 (#16993)
Charles Xu
2025-11-11 12:20:31 +01:00
-
4a5b8aff40
cmake : add version to all shared object files (#17091)
Mike Abbott
2025-11-11 04:19:50 -07:00
-
d2d626938a
Install rpc-server when GGML_RPC is ON. (#17149)
Nicolas B. Pierron
2025-11-11 11:53:59 +01:00
-
2fc392ce35
convert : register UMT5Model architecture for T5 conversion (#17160)
levkropp
2025-11-11 03:38:30 -05:00
-
ece0f5c177
opencl: add fastdiv and use it in set_rows, ported from cuda (#17090)
lhez
2025-11-10 15:00:13 -08:00
-
7bef684118
models : move build_inp_out_ids outside loop (#17151)
Sigbjørn Skjæret
2025-11-10 22:55:30 +01:00
-
395e286bc9
cpu: skip NOPs to avoid barriers (#17133)
Max Krasnyansky
2025-11-10 12:44:49 -08:00
-
13730c183b
metal : cap threadgroups size of set_rows (#17146)
Georgi Gerganov
2025-11-10 21:33:35 +02:00
-
967eb4b2bf
ggml-cpu : inspect -march and -mcpu to found the CPU (#16333)
Adrien Gallouët
2025-11-10 20:03:36 +01:00
-
f117be185e
vulkan: check glslc executable string (#17144)
Ruben Ortlam
2025-11-10 16:59:26 +01:00
-
85234a4b3a
vulkan: fix validation issue introduced by #16868 (#17145)
Ruben Ortlam
2025-11-10 16:59:10 +01:00
-
0c74f32632
memory: Hybrid context shift (#17009)
Gabe Goodhart
2025-11-10 08:14:23 -07:00
-
c27efd2bd1
metal : enable tensor API for A19 (#17087)
Georgi Gerganov
2025-11-10 15:38:42 +02:00
-
df70bedda7
arm64: add i8mm route with SVE ggml_vec_dot_q4_K_q8_K and ggml_vec_dot_q6_K_… (#15277)
fj-y-saito
2025-11-10 22:12:59 +09:00
-
f914544b16
batched-bench : add "separate text gen" mode (#17103)
Georgi Gerganov
2025-11-10 12:59:29 +02:00
-
4b13a684c5
mtmd: fix patch_size initialized to random value in audio models (#17128)
Xuan-Son Nguyen
2025-11-10 11:41:05 +01:00
-
9898b57cbe
editorconfig : ignore benches/ (#17140)
Georgi Gerganov
2025-11-10 12:17:19 +02:00