Georgi Gerganov
b11f9ba9b8
server : remove hack for extra parallel slot ( #10187 )
...
ggml-ci
2024-11-06 13:29:01 +02:00
Diego Devesa
94d8cb8be1
metal : fix from ptr buffer name ( #10189 )
2024-11-06 12:10:07 +01:00
Georgi Gerganov
1dc04b2dee
ggml : adjust is_first_call init value ( #10193 )
...
ggml-ci
2024-11-06 11:20:10 +02:00
Georgi Gerganov
a1eaf6a960
metal : add quantized FA support ( #10149 )
...
* metal : add quantized FA (vec) support
ggml-ci
* metal : add quantized FA (non-vec) support
* metal : fix support check
ggml-ci
* metal : clean-up
* metal : clean-up (cont)
* metal : fix shared memory calc + reduce smem + comments
* metal : float-correctness
* metal : minor [no ci]
2024-11-06 10:24:23 +02:00
Gabe Goodhart
b8deef0ec0
llama : add <|tool_call|> formatting to Granite template ( #10177 )
...
Branch: GraniteToolCallTemplate
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
2024-11-05 14:23:04 +02:00
Diego Devesa
a9e8a9a030
ggml : fix arch check in bf16_to_fp32 ( #10164 )
2024-11-04 23:17:01 +01:00
Eve
3407364776
Q6_K AVX improvements ( #10118 )
...
* q6_k instruction reordering attempt
* better subtract method
* should be theoretically faster
small improvement with shuffle lut, likely because all loads are already done at that stage
* optimize bit fiddling
* handle -32 offset separately. bsums exists for a reason!
* use shift
* Update ggml-quants.c
* have to update ci macos version to 13 as 12 doesnt work now. 13 is still x86
2024-11-04 23:06:31 +01:00
Diego Devesa
d5a409e57f
ggml : fix gelu tables initialization ( #10172 )
2024-11-04 20:06:58 +01:00
Diego Devesa
401558b7ba
ggml : fix q4xx mat mul, increase ggml_aligned_malloc alignment ( #10167 )
2024-11-04 17:34:08 +01:00
Xuan Son Nguyen
9e0ecfb697
server : clarify /slots endpoint, add is_processing ( #10162 )
...
* server : clarify /slots endpoint, add is_processing
* fix tests
2024-11-04 16:33:29 +01:00
snadampal
6a066b9978
fix build break on arm64 linux ( #10166 )
...
This fixes the build break from the recent changes
to move the CPU backend to separate files
https://github.com/ggerganov/llama.cpp/pull/10144
2024-11-04 16:08:33 +01:00
Diego Devesa
ea02c753eb
cuda : clear error after changing peer access ( #10153 )
2024-11-04 13:10:23 +01:00
Georgi Gerganov
05697f670b
metal : simplify f16 and f32 dequant kernels ( #0 )
2024-11-04 13:49:34 +02:00
Georgi Gerganov
f8e58135cf
metal : move dequantize templates to beginning of MSL source ( #0 )
2024-11-04 13:44:06 +02:00
leo-pony
329ed914c9
CANN: adjust backend registry refactor. ( #10158 )
...
remove buffer->iface.get_name that used in cann as it was removed in backend registry refactor PR.
2024-11-04 19:08:22 +08:00
Georgi Gerganov
ce027adfb3
sync : ggml
2024-11-04 10:33:37 +02:00
Yuri Khrustalev
284e5b0275
cmake : make it possible linking ggml as external lib (ggml/1003)
2024-11-04 10:33:11 +02:00
Plamen Minev
e2292aaa17
metal : fix minor string leaks (ggml/1004)
2024-11-04 10:33:10 +02:00
Diego Devesa
9f40989351
ggml : move CPU backend to a separate file ( #10144 )
2024-11-03 19:34:08 +01:00
Georgi Gerganov
08828a6d7d
metal : minor fixup in FA kernel ( #10143 )
...
* metal : minor fixup in FA kernel
ggml-ci
* metal : use the unrolled loop variable
* metal : remove unused var
2024-11-03 15:18:40 +02:00
Georgi Gerganov
1839f69130
flake.lock: Update ( #10146 )
2024-11-03 05:14:15 -08:00
Christian Köhnenkamp
9830b6923b
Add apple arm to presets ( #10134 )
...
* Add apple arm to presets
* Add final new line
2024-11-02 15:35:31 -07:00
sasha0552
42cadc74bd
server : fix slot selection by lru ( #10126 )
...
* server : fix slot selection by lru, migrate lcs to `size_t`
* minor debug log fix
2024-11-02 18:34:56 +02:00
Georgi Gerganov
45950415ed
server : fix endpoint checks ( #10135 )
...
ggml-ci
2024-11-02 18:34:00 +02:00
Georgi Gerganov
1926d6e39d
llama : adjust default context size + print warnings ( #10136 )
...
* llama : adjust default context size + print warnings
ggml-ci
* ggml-ci : add missing gpu-layers + adjust context sizes
2024-11-02 15:18:56 +02:00
Diego Devesa
b634f8a26f
simple-chat : only add bos on first prompt ( #10129 )
2024-11-02 13:08:53 +01:00
Xuan Son Nguyen
7554aa4655
convert-lora : make --base optional ( #10110 )
...
* convert-lora : make `--base` optional
* lint
* handle case where base_model_name_or_path is invalid
* do not include metadata from base model
* clarify unspecified --base
* add small comment [no ci]
* trigger ci
2024-11-02 12:53:17 +01:00
Diego Devesa
a6744e43e8
llama : add simple-chat example ( #10124 )
...
* llama : add simple-chat example
---------
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
2024-11-01 23:50:59 +01:00
Diego Devesa
e991e3127f
llama : use smart pointers for ggml resources ( #10117 )
2024-11-01 23:48:26 +01:00
Shupei Fan
418f5eef26
vulkan : improve ggml_vk_create_buffer error handling ( #9898 )
2024-11-01 19:33:14 +01:00
Georgi Gerganov
ba6f62eb79
readme : update hot topics
2024-11-01 17:31:51 +02:00
sasha0552
d865d1478c
server : fix smart selection of available slot ( #10120 )
...
* Fix smart selection of available slot
* minor fix
* replace vectors of tokens with shorthands
2024-11-01 14:33:14 +01:00
Georgi Gerganov
1804adb0cf
ggml : remove ggml_scratch ( #10121 )
...
ggml-ci
2024-11-01 12:58:45 +02:00
Georgi Gerganov
815fe72adc
sync : ggml
2024-11-01 10:28:24 +02:00
Georgi Gerganov
f221d56220
ggml : alloc ggml_contexts on the heap (whisper/2525)
2024-11-01 10:24:50 +02:00
Zhenwei Jin
e597e50794
build: fix build error in Windows env with OneAPI setup ( #10107 )
2024-11-01 11:09:59 +08:00
Diego Devesa
85679d37f3
llama : improve output buffer type selection ( #10098 )
2024-11-01 00:49:53 +01:00
Diego Devesa
1e9f94994e
quantize : fix --keep-split ( #10114 )
2024-11-01 00:45:34 +01:00
Diego Devesa
c02e5ab2a6
llama : fix buffer checks for mamba and rwk ( #10111 )
...
* llama : fix buffer checks for mamba and rwk
* llama : fix missing worst case flag during reserve
* cuda : fix supports_op for norm
* disable sched SET_CAUSE
2024-10-31 22:54:23 +01:00
Zhenwei Jin
ab3d71f97f
loader: refactor tensor weights storage ( #9935 )
...
* loader: refactor tensor weights storage
* use sorted map, sort weights by layer
---------
Co-authored-by: slaren <slarengh@gmail.com>
2024-10-31 19:50:39 +01:00
Kevin Gibbons
0a683e8088
server : include scheme when printing URL ( #10106 )
2024-10-31 14:02:35 +01:00
Diego Devesa
dea5e86051
ggml : check tensor name lengths in gguf files ( #10100 )
2024-10-31 11:40:59 +01:00
Sergio López
1329c0a75e
kompute: add mul_mat_q4_k shader ( #10097 )
...
This is a more or less direct translation from the Metal implementation
to GLSL.
Signed-off-by: Sergio Lopez <slp@redhat.com>
2024-10-31 11:09:52 +02:00
Sergio López
61408e7fad
kompute: add backend registry / device interfaces ( #10045 )
...
Get in line with the other backends by supporting the newer
backend/device registry interfaces.
Signed-off-by: Sergio Lopez <slp@redhat.com>
2024-10-30 17:01:52 +01:00
Diego Devesa
b9e02e8184
ggml : fix memory leaks when loading invalid gguf files ( #10094 )
...
* ggml : fix gguf string leak when reading kv pairs fails
* ggml : avoid crashing with GGML_ABORT when the KV has an invalid type
* ggml : avoid crashing on failed memory allocations when loading a gguf file
2024-10-30 14:51:21 +01:00
Rich Dougherty
6763f713bb
readme : more lora detail in main example readme ( #10064 )
2024-10-30 13:22:39 +01:00
Rich Dougherty
79a2bc042d
convert : more detailed convert lora usage docs ( #10065 )
2024-10-30 13:22:21 +01:00
xctan
fc83a9e584
ggml : add Q4_0_8_8 RISC-V GEMV and GEMM kernels ( #10029 )
...
* ggml : RISC-V vector gemv for q4_0_8x8
* ggml : Added WIP rvv q4_0_8x8 gemm
* ggml : Added initial implementation of rvv gemm
* ggml : optimize gemm to avoid register spillover
* ggml : Fix GCC rvv load alignment issue
* ggml : Format gemm rvv code
* ggml : Fix a typo in RVV q4_0_8_8 GEMM
2024-10-30 09:00:40 +02:00
Diego Devesa
c5b0f4b5d9
llama : refactor model loader with backend registry ( #10026 )
2024-10-30 02:01:23 +01:00
Changyeon Kim
8f275a7c45
ggml: Add POOL2D OP for GPU acceleration to the Vulkan backend in the MobileVLM model. ( #9763 )
...
* ggml: Add POOL2D OP for GPU ACC to the Vulkan.
- The MobileVLM model now supports inference acceleration through GPU by utilizing the Vulkan backend.
- A GGML_OP_POOL_2D shader has been added. (Pooling)
- The encoding performance of the CLIP model improved from 2.8s on the CPU to 0.7s on the GPU.
Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>
* [fix] Correct the incorrect order of the parameters.
fix casting to int.
Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>
---------
Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>
2024-10-29 09:52:56 +01:00
