]>
git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/log
Georgi Gerganov [Sat, 13 Jan 2024 22:13:17 +0000 (00:13 +0200)]
talk-llama : sync llama.cpp
Georgi Gerganov [Sat, 13 Jan 2024 22:12:17 +0000 (00:12 +0200)]
sync : ggml
Georgi Gerganov [Sat, 13 Jan 2024 22:09:26 +0000 (00:09 +0200)]
examples : adapt to metal API
Johannes Gäßler [Sat, 13 Jan 2024 20:41:37 +0000 (21:41 +0100)]
ggml: cache sin/cos for RoPE (llama/4908)
Georgi Gerganov [Sat, 13 Jan 2024 18:45:45 +0000 (20:45 +0200)]
metal : remove old API (llama/4919)
ggml-ci
Georgi Gerganov [Sat, 13 Jan 2024 16:46:37 +0000 (18:46 +0200)]
metal : disable log for loaded kernels (llama/4794)
texmex76 [Sat, 13 Jan 2024 16:06:20 +0000 (17:06 +0100)]
gguf : fix potential infinite for-loop (llama/4600)
Co-authored-by: Bernhard Gstrein <redacted>
Georgi Gerganov [Sat, 13 Jan 2024 16:03:45 +0000 (18:03 +0200)]
metal : refactor kernel loading code (llama/4794)
* metal : detect more GPU families
* metal : refactor kernel loading
* metal : set kernel family requirements
* metal : fix kernel init + fix compile options
* metal : take into account simdgroup reduction support
* metal : print only skipped kernels
* metal : fix check for simdgroup reduction support
* metal : check for Metal 3
* metal : free allocations
* metal : normalize encoder:setComputePipelineStatus calls
ggml-ci
* metal : fix Metal3 family check
ggml-ci
* metal : check for simdgroup matrix mul. feature
ggml-ci
Johannes Gäßler [Fri, 12 Jan 2024 19:38:54 +0000 (20:38 +0100)]
CUDA: faster q8_0 -> f16 dequantization (llama/4895)
RhinoDevel [Sat, 13 Jan 2024 18:51:35 +0000 (19:51 +0100)]
talk-llama : add optional CLI arg to set the bot name (#1764)
james wolf [Sat, 13 Jan 2024 17:37:18 +0000 (12:37 -0500)]
examples : add python example for transcription (#1744)
* rebase and add simple python interface
* moved python files to examples/python
Georgi Gerganov [Sat, 13 Jan 2024 15:47:40 +0000 (17:47 +0200)]
whisper : load the model into multiple buffers of max size 1GB (#1763)
Georgi Gerganov [Fri, 12 Jan 2024 20:04:51 +0000 (22:04 +0200)]
talk-llama : sync llama.cpp
Georgi Gerganov [Fri, 12 Jan 2024 19:56:50 +0000 (21:56 +0200)]
sync : ggml
slaren [Fri, 12 Jan 2024 19:38:34 +0000 (20:38 +0100)]
backend_sched : fix assignments
ggml-ci
slaren [Fri, 12 Jan 2024 19:07:38 +0000 (20:07 +0100)]
llama : ggml-backend integration (llama/4766)
* llama : ggml-backend integration
* ggml-backend : add names to buffers
* fix unmap after loading
* batched-bench : add tensor_split param
* llama : check for null tensor_split
* ggml-backend : increase GGML_MAX_BACKENDS
* improve graph splitting, partial fix for --no-kv-offload
* cuda : add ggml-backend split buffer support
* cuda : do not create buffer types for devices that don't exist (fixes usage without CUDA devices available)
* ggml : fix null backend dereference (llama/4807)
* ggml : fix null backend dereference
* ggml : also check ggml_backend_is_cpu
* test-backend-ops : check buffer allocation failures
* llama : add cparam (split_mode) and command line argument (--split-mode, -sm) to configure the split mode (none, layer or row)
* ggml : fix mul_mat_id work size
* llama : rewrite session kv load/set without graphs
* minor
* llama : only initialize used backends, free backends on context free
* llama : abort ctx if cuda backend init fails
* llama : rewrite lora with ggml-backend and compute on CPU
ggml-ci
* llama : only map to a backend buffer the region of the file mapping containing the tensors used in the buffer
* opencl : add ggml-backend buffer type
* cuda : only use batched_cublas with batched mat muls (fixes fp16 tg perf)
* llama : on Metal, by default offload the full model
ggml-ci
* metal : page align the data ptr (llama/4854)
* Apply suggestions from code review
Co-authored-by: Johannes Gäßler <redacted>
* cuda : fix split buffer free
* address review comments
* llama-bench : add split-mode parameter
* fix whitespace
* opencl : fix double initialization
* server : add --split-mode parameter
* use async copy and compute to improve multi-gpu performance
ggml-ci
* use async memcpys to copy the graph outputs to the CPU
* fix opencl
* use a host buffer for the cpu compute buffer for faster copies to the gpu
---------
Co-authored-by: Georgi Gerganov <redacted>
Co-authored-by: Johannes Gäßler <redacted>
Johannes Gäßler [Fri, 12 Jan 2024 11:30:41 +0000 (12:30 +0100)]
CUDA: fix softmax compile for old CUDA versions (llama/4862)
Kawrakow [Fri, 12 Jan 2024 05:59:57 +0000 (06:59 +0100)]
Importance Matrix calculation (llama/4861)
* imatrix: 1st version
* imatrix: WIP
* Cleanup
* Update examples/imatrix/imatrix.cpp
Co-authored-by: Georgi Gerganov <redacted>
---------
Co-authored-by: Iwan Kawrakow <redacted>
Co-authored-by: Georgi Gerganov <redacted>
Sơn Phan Trung [Fri, 12 Jan 2024 12:11:04 +0000 (19:11 +0700)]
models : make all scripts to be POSIX Compliant (#1725)
* download-coreml-model: make it POSIX-compliant
* download-ggml-model: posix compliant (2nd)
* minor edit
* forgot to add newline
* generate-coreml-interface: far more straightforward
* generate-coreml-model: done with the posix thingy
* typo
* Update download-ggml-model.sh
* fix
* fix typo
* another fix
* Update download-coreml-model.sh
* Update download-ggml-model.sh
* Update download-coreml-model.sh
Georgi Gerganov [Fri, 12 Jan 2024 12:02:30 +0000 (14:02 +0200)]
ggml : fix 32-bit ARM compat for IQ2_XS (#1758)
* ggml : fix 32-bit ARM compat
* ggml : fix fix
* ggml : fix fix fix
Boris Bliznioukov [Fri, 12 Jan 2024 11:44:50 +0000 (14:44 +0300)]
go : add SetInitialPrompt method to bindings (#1753)
George Hindle [Fri, 12 Jan 2024 11:42:52 +0000 (11:42 +0000)]
server : add more parameters to server api (#1754)
* feat(server): add more parameters to server api
* fix(server): reset params to original parsed values for each request
Georgi Gerganov [Fri, 12 Jan 2024 11:37:38 +0000 (13:37 +0200)]
whisper : fix segment length with params.no_timestamps == true
George Hindle [Fri, 12 Jan 2024 11:24:38 +0000 (11:24 +0000)]
params : don't compute timestamps when not printing them (#1755)
Georgi Gerganov [Thu, 11 Jan 2024 20:10:10 +0000 (22:10 +0200)]
talk-llama : sync llama.cpp
Georgi Gerganov [Thu, 11 Jan 2024 20:00:12 +0000 (22:00 +0200)]
swift : remove local ggml.h reference
Georgi Gerganov [Thu, 11 Jan 2024 19:57:40 +0000 (21:57 +0200)]
swift : track ggml release branch
Georgi Gerganov [Thu, 11 Jan 2024 19:54:17 +0000 (21:54 +0200)]
sync : ggml
Georgi Gerganov [Thu, 11 Jan 2024 19:49:13 +0000 (21:49 +0200)]
sync : llama.cpp
Kawrakow [Thu, 11 Jan 2024 19:39:39 +0000 (20:39 +0100)]
ggml : SOTA 2-bit quants (add IQ2_XS) (llama/4856)
* iq2_xs: basics
* iq2_xs: this should have been in the basics
* iq2_xs: CUDA and scalar CPU works
* iq2_xs: WIP Metal
* iq2_xs: Metal now works
* iq2_xs: working, but dog slow, ARM_NEON dot product
* iq2_xs: better ARM_NEON dot product
We are now at 19.5 t/s for TG-128 and 61 t/s for PP-512 when
running on the CPU.
* iq2_xs: AVX2 dot product - 19.5 t/s
* iq2_xs: faster AVX2 dit product
21.4 t/s for TG-128, 59.2 t/s for PP-512.
The latter is 2x compared to the previous version.
* iq2_xs: had forgotten to delete iq2-data.h
* Add llama enum for IQ2_XS
---------
Co-authored-by: Iwan Kawrakow <redacted>
Paul Tsochantaris [Thu, 11 Jan 2024 14:31:52 +0000 (14:31 +0000)]
metal : put encoder debug group behind a define (llama/4873)
Georgi Gerganov [Tue, 9 Jan 2024 17:37:08 +0000 (19:37 +0200)]
metal : improve dequantize precision to match CPU (llama/4836)
ggml-ci
Georgi Gerganov [Tue, 9 Jan 2024 08:42:06 +0000 (10:42 +0200)]
ggml : fix vld1q_s8_x4 32-bit compat (llama/4828)
* ggml : fix vld1q_s8_x4 32-bit compat
ggml-ci
* ggml : fix 32-bit ARM compat (cont)
ggml-ci
Johannes Gäßler [Tue, 9 Jan 2024 07:58:55 +0000 (08:58 +0100)]
CUDA: faster softmax via shared memory + fp16 math (llama/4742)
Georgi Gerganov [Thu, 11 Jan 2024 07:34:59 +0000 (09:34 +0200)]
metal : fix deprecation warning (ggml/690)
Timothy Cronin [Thu, 11 Jan 2024 07:27:48 +0000 (02:27 -0500)]
ggml : remove ggml_cpy_inplace and ggml_cont_inplace (ggml/693)
Jack Mousseau [Wed, 10 Jan 2024 14:19:19 +0000 (06:19 -0800)]
metal : wrap each operation in debug group (ggml/690)
leejet [Wed, 10 Jan 2024 13:13:42 +0000 (21:13 +0800)]
ggml : change GGML_MAX_NAME at compile time (ggml/682)
* change GGML_MAX_NAME to 128
* allow controlling the value of GGML_MAX_NAME through external macro definitions
Halalaluyafail3 [Tue, 9 Jan 2024 16:16:37 +0000 (11:16 -0500)]
Fix execlp call (ggml/689)
NULL can be an integer constant expression with the value zero, in this case the behavior would be undefined because of an incorrect type being passed to the variable arguments.
Kawrakow [Mon, 8 Jan 2024 15:02:32 +0000 (16:02 +0100)]
SOTA 2-bit quants (llama/4773)
* iq2_xxs: basics
* iq2_xxs: scalar and AVX2 dot products
Needed to change Q8_K to have quants in the -127...127 range,
else the IQ2_XXS AVX implementation becomes very awkward.
The alternative would have been to use Q8_0 instead. Perhaps
I'll change later, for now this is what we have.
* iq2_xxs: ARM_NEON dot product
Somehow strangely slow (112 ms/token).
* iq2_xxs: WIP Metal
Dequantize works, something is still wrong with the
dot product.
* iq2_xxs: Metal dot product now works
We have
PP-512 = 475 t/s
TG-128 = 47.3 t/s
Not the greatest performance, but not complete garbage either.
* iq2_xxs: slighty faster dot product
TG-128 is now 48.4 t/s
* iq2_xxs: slighty faster dot product
TG-128 is now 50.9 t/s
* iq2_xxs: even faster Metal dot product
TG-128 is now 54.1 t/s.
Strangely enough, putting the signs lookup table
into shared memory has a bigger impact than the
grid values being in shared memory.
* iq2_xxs: dequantize CUDA kernel - fix conflict with master
* iq2_xxs: quantized CUDA dot product (MMVQ)
We get TG-128 = 153.1 t/s
* iq2_xxs: slightly faster CUDA dot product
TG-128 is now at 155.1 t/s.
* iq2_xxs: add to llama ftype enum
* iq2_xxs: fix MoE on Metal
* Fix missing MMQ ops when on hipBLAS
I had put the ggml_supports_mmq call at the wrong place.
* Fix bug in qequantize_row_iq2_xxs
The 0.25f factor was missing.
Great detective work by @ggerganov!
* Fixing tests
* PR suggestion
---------
Co-authored-by: Iwan Kawrakow <redacted>
Johannes Gäßler [Sun, 7 Jan 2024 16:24:08 +0000 (17:24 +0100)]
CUDA: fixed redundant value dequantization (llama/4809)
Konstantin Zhuravlyov [Sun, 7 Jan 2024 06:52:42 +0000 (01:52 -0500)]
ggml : use __builtin_amdgcn_sudot4 in __dp4a for gfx11 (llama/4787)
Georgi Gerganov [Fri, 5 Jan 2024 13:18:21 +0000 (15:18 +0200)]
ggml : do not sched_yield when calling BLAS (llama/4761)
* ggml : do not sched_yield when calling BLAS
ggml-ci
* ggml : fix do_yield logic
ggml-ci
* ggml : simplify do_yield logic
ggml-ci
Georgi Gerganov [Thu, 4 Jan 2024 08:12:26 +0000 (10:12 +0200)]
ggml : include stdlib.h before intrin.h (llama/4736)
Alexandru Mariuti [Wed, 10 Jan 2024 16:12:06 +0000 (17:12 +0100)]
swift : checkout ggml commit instead of branch (#1750)
RhinoDevel [Wed, 10 Jan 2024 14:15:28 +0000 (15:15 +0100)]
talk-llama : add optional Piper TTS support (#1749)
Add commented-out command to optionally use Piper (https://github.com/rhasspy/piper) as text-to-speech solution for the talk-llama example. Piper voices sound almost like real people which is a big improvement (e.g.) from something like espeak.
Emmanuel Schmidbauer [Mon, 8 Jan 2024 22:39:51 +0000 (17:39 -0500)]
server : add request path option(#1741)
Georgi Gerganov [Mon, 8 Jan 2024 14:41:28 +0000 (16:41 +0200)]
main : add cli option to disable system prints (#1740)
Georgi Gerganov [Sun, 7 Jan 2024 11:35:14 +0000 (13:35 +0200)]
server : fix server temperature + add temperature_inc (#1729)
* server : fix server temperature + add temperature_inc
* server : change dashes to underscores in parameter names
Georgi Gerganov [Sat, 6 Jan 2024 15:22:57 +0000 (17:22 +0200)]
talk-llama : sync latest llama.cpp
Georgi Gerganov [Fri, 5 Jan 2024 15:11:27 +0000 (17:11 +0200)]
release : v1.5.4
Erik Scholz [Fri, 5 Jan 2024 15:00:00 +0000 (16:00 +0100)]
fix : cuda order of synchronization when setting a buffer (ggml/679)
* fix : cuda order of synchronization when setting a buffer
* also sync before memcpy
---------
Co-authored-by: slaren <redacted>
Georgi Gerganov [Fri, 5 Jan 2024 14:30:52 +0000 (16:30 +0200)]
metal : switch back to default.metallib (ggml/681)
ggml-ci
Georgi Gerganov [Fri, 5 Jan 2024 13:36:04 +0000 (15:36 +0200)]
ggml : fix q2_k bpw in comments (ggml/680)
Yajing Tang [Thu, 4 Jan 2024 14:28:30 +0000 (06:28 -0800)]
coreml : fix ANE optimized encoder (#1716)
Georgi Gerganov [Thu, 4 Jan 2024 12:47:42 +0000 (14:47 +0200)]
whisper.swiftui : add .gitignore
Georgi Gerganov [Thu, 4 Jan 2024 11:37:25 +0000 (13:37 +0200)]
whispser : reset the "batched" timings (#1721)
Georgi Gerganov [Wed, 3 Jan 2024 17:36:33 +0000 (19:36 +0200)]
release : v1.5.3
Ashraful Islam [Wed, 3 Jan 2024 17:30:26 +0000 (11:30 -0600)]
swift : update Package.swift to use ggml as package dependency (#1701)
* updates Package.swift to use ggml as dependency
* cleans up the Package.swift file by removing redundant source files
* updates ggml url src to ggerganov
Finn Voorhees [Wed, 3 Jan 2024 13:39:43 +0000 (08:39 -0500)]
ggml : add error handling to graph_compute (#1714)
Georgi Gerganov [Wed, 3 Jan 2024 12:18:46 +0000 (14:18 +0200)]
cuda : simplify expression
Co-authored-by: slaren <redacted>
Georgi Gerganov [Wed, 3 Jan 2024 11:01:44 +0000 (13:01 +0200)]
cuda : mark I16 and I32 ops as unsupported
ggml-ci
Georgi Gerganov [Wed, 3 Jan 2024 09:35:46 +0000 (11:35 +0200)]
metal : add kernel_get_rows_i32
ggml-ci
Georgi Gerganov [Tue, 2 Jan 2024 19:07:47 +0000 (21:07 +0200)]
metal : optimize ggml_mul_mat_id (faster Mixtral PP) (llama/4725)
* ggml : disable fast-math for Metal (cmake build only)
ggml-ci
* metal : fix Metal API debug warnings
* cmake : add -fno-inline for Metal build (llama/4545)
* metal : fix API debug warnings
* metal : fix compile warnings
* metal : use uint64_t for strides
* cmake : rename option to LLAMA_METAL_SHADER_DEBUG
* metal : fix mat-vec Q8_0 kernel for BS > 1
* metal : normalize mat-vec kernel signatures
* cmake : respect LLAMA_QKK_64 option
* metal : fix mat-vec Q4_K kernel for QK_K == 64
* metal : optimizing ggml_mul_mat_id (wip)
* metal : minor fix
* metal : opt mul_mm_id
Georgi Gerganov [Tue, 2 Jan 2024 08:57:44 +0000 (10:57 +0200)]
metal : enable shader debugging (cmake option) (llama/4705)
* ggml : disable fast-math for Metal (cmake build only)
ggml-ci
* metal : fix Metal API debug warnings
* cmake : add -fno-inline for Metal build (llama/4545)
* metal : fix API debug warnings
* metal : fix compile warnings
* metal : use uint64_t for strides
* cmake : rename option to LLAMA_METAL_SHADER_DEBUG
* metal : fix mat-vec Q8_0 kernel for BS > 1
* metal : normalize mat-vec kernel signatures
* cmake : respect LLAMA_QKK_64 option
* metal : fix mat-vec Q4_K kernel for QK_K == 64
ggml-ci
Georgi Gerganov [Sun, 31 Dec 2023 09:43:31 +0000 (11:43 +0200)]
ggml : add ggml_vdotq_s32 alias (llama/4715)
ggml-ci
Johannes Gäßler [Sat, 30 Dec 2023 12:52:01 +0000 (13:52 +0100)]
CUDA: fixed tensor cores not being used on RDNA3 (llama/4697)
automaticcat [Sat, 30 Dec 2023 08:07:48 +0000 (15:07 +0700)]
ggml : add ggml_cpu_has_avx_vnni() (llama/4589)
* feat: add avx_vnni based on intel documents
* ggml: add avx vnni based on intel document
* llama: add avx vnni information display
* docs: add more details about using oneMKL and oneAPI for intel processors
* docs: add more details about using oneMKL and oneAPI for intel processors
* docs: add more details about using oneMKL and oneAPI for intel processors
* docs: add more details about using oneMKL and oneAPI for intel processors
* docs: add more details about using oneMKL and oneAPI for intel processors
* Update ggml.c
Fix indentation upgate
Co-authored-by: Georgi Gerganov <redacted>
---------
Co-authored-by: Georgi Gerganov <redacted>
Johannes Gäßler [Fri, 29 Dec 2023 22:12:53 +0000 (23:12 +0100)]
CUDA: fix tensor core logic for Pascal and HIP (llama/4682)
hydai [Fri, 29 Dec 2023 16:31:19 +0000 (00:31 +0800)]
cuda: fix vmm oom issue on NVIDIA AGX Orin (llama/4687)
Signed-off-by: hydai <redacted>
Guillaume Wenzek [Fri, 29 Dec 2023 17:07:03 +0000 (18:07 +0100)]
ggml : extend ggml_get_rows, ggml_repeat, ggml_concat (ggml/639)
* add more int ops
* ggml_compute_forward_dup_bytes
* add tests
* PR comments
* tests : minor indentations
---------
Co-authored-by: Georgi Gerganov <redacted>
Georgi Gerganov [Wed, 3 Jan 2024 09:42:42 +0000 (11:42 +0200)]
scripts : fix sync order + metal sed
Andreu Huguet [Tue, 2 Jan 2024 16:50:04 +0000 (17:50 +0100)]
examples : fix WASM Stack Overflow (#1713)
Fix for problem:
"""
RuntimeError: Aborted(Stack overflow! Stack cookie has been overwritten at 0x12be2b10, expected hex dwords 0x89BACDFE and 0x2135467, but received 0x00000000 0x00000000)
"""
That appears when executing the WASM example with the newer versions.
bobqianic [Sat, 30 Dec 2023 21:12:31 +0000 (21:12 +0000)]
docker : fix the publishing of the CUDA Docker image (#1704)
Georgi Gerganov [Fri, 29 Dec 2023 13:00:46 +0000 (15:00 +0200)]
scripts : do not sync commits from this repo
Tamotsu Takahashi [Fri, 29 Dec 2023 10:23:27 +0000 (19:23 +0900)]
ci : build with CLBlast + ggml-opencl use GGML_API (#1576)
* Build with CLBlast
* Declare GGML_API
After rebasing, examples/talk-llama failed:
"D:\a\whisper.cpp\whisper.cpp\build\ALL_BUILD.vcxproj" (build target) (1) ->
"D:\a\whisper.cpp\whisper.cpp\build\examples\talk-llama\talk-llama.vcxproj" (default target) (14) ->
(Link target) ->
llama.obj : error LNK2019: unresolved external symbol ggml_cl_free_data referenced in function "public: __cdecl llama_model::~llama_model(void)" (??1llama_model@@QEAA@XZ) [D:\a\whisper.cpp\whisper.cpp\build\examples\talk-llama\talk-llama.vcxproj]
llama.obj : error LNK2019: unresolved external symbol ggml_cl_transform_tensor referenced in function "public: void __cdecl llama_model_loader::load_all_data(struct ggml_context *,void (__cdecl*)(float,void *),void *,struct llama_mlock *)" (?load_all_data@llama_model_loader@@QEAAXPEAUggml_context@@P6AXMPEAX@Z1PEAUllama_mlock@@@Z) [D:\a\whisper.cpp\whisper.cpp\build\examples\talk-llama\talk-llama.vcxproj]
D:\a\whisper.cpp\whisper.cpp\build\bin\Release\talk-llama.exe : fatal error LNK1120: 2 unresolved externals [D:\a\whisper.cpp\whisper.cpp\build\examples\talk-llama\talk-llama.vcxproj]
bobqianic [Fri, 29 Dec 2023 09:38:35 +0000 (09:38 +0000)]
whisper : replace `tensor->n_dims` with `ggml_n_dims(tensor)` (#1694)
Georgi Gerganov [Fri, 29 Dec 2023 09:30:47 +0000 (11:30 +0200)]
sync : ggml (VMM, sync-ggml-am, dotprod ARM fixes, CUDA fixes) (#1691)
* scripts : add sync-ggml-am.sh
* sync : ggml (VMM, ARM dot prod fix, etc.)
* build : fix CUDA build
* ggml : fix some mul mat cases + add tests for src1 F16
https://github.com/ggerganov/ggml/commit/
dbd02958fa4f46898f68ca29c27ddcdc58a06f98
Dimo [Fri, 29 Dec 2023 09:14:32 +0000 (10:14 +0100)]
download : fix large q5 model name (#1695)
fixed typo in large-v3-q5-0 model name to match HF link
bobqianic [Sat, 23 Dec 2023 12:02:58 +0000 (12:02 +0000)]
whisper : Replace WHISPER_PRINT_DEBUG with WHISPER_LOG_DEBUG (#1681)
Georgi Gerganov [Fri, 22 Dec 2023 15:53:39 +0000 (17:53 +0200)]
sync : ggml (ggml_scale, ggml_row_size, etc.) (#1677)
* sync : ggml
* sync : llama.cpp
* talk-llama : fix obsolete param
* ggml-alloc : fix ggml_tallocr_is_own
* talk.wasm : update to new ggml
* ggml : fix type punning in ggml_scale
* ggml : cuda jetson + arm quants warnings
Chaoqun [Fri, 22 Dec 2023 11:16:02 +0000 (19:16 +0800)]
docker : Dockerize whisper.cpp (#1674)
* build: add dockerfile for ci
* ci: add action to build/push docker image
* fix: lowercase repository to fix ci
* ci: update cuBLAS flag
* build: install curl and ffmped in image
* docs: add docker section
* fix: improve args check when download model
bobqianic [Thu, 21 Dec 2023 22:39:46 +0000 (22:39 +0000)]
CI : Add coverage for talk-llama when WHISPER_CUBLAS=1 (#1672)
bobqianic [Thu, 21 Dec 2023 20:48:52 +0000 (20:48 +0000)]
examples : Revert CMakeLists.txt for talk-llama (#1669)
bobqianic [Thu, 21 Dec 2023 13:44:04 +0000 (13:44 +0000)]
cmake : set default CUDA architectures (#1667)
Alfredo Montesinos [Tue, 19 Dec 2023 10:40:14 +0000 (04:40 -0600)]
bench.py : add different large models (#1655)
Amend different large v1,v2,v3 models to benchmark.
Georgi Gerganov [Thu, 14 Dec 2023 20:00:47 +0000 (22:00 +0200)]
wchess : update README.md
Georgi Gerganov [Thu, 14 Dec 2023 15:56:11 +0000 (17:56 +0200)]
release : v1.5.2
Georgi Gerganov [Thu, 14 Dec 2023 15:51:14 +0000 (17:51 +0200)]
wchess : update readme
fraxy-v [Thu, 14 Dec 2023 13:58:26 +0000 (15:58 +0200)]
wchess : whisper assisted chess (#1595)
* wchess: whisper assisted chess
* wchess: fix allowed moves in check
* wchess: touchstart, touchend events
* wchess: css, disabled button
* wchess : html touches
* wchess : minor fixes and code style
* wchess : bump encoder context to 1280
* wchess : index.html
* wchess : fix CI warnings
* wchess : add array header
* wchess : build static library
* wchess : display grammar
* wchess : update UX
* wchess : add comment
* wchess : add README
---------
Co-authored-by: Georgi Gerganov <redacted>
Georgi Gerganov [Wed, 13 Dec 2023 19:55:03 +0000 (21:55 +0200)]
sync : ggml (Metal fixes, new ops, tests) (#1633)
* sync : ggml (Metal fixes, new ops, tests)
* cuda : fix bin bcast when src1 and dst have different types
Kreijstal [Tue, 12 Dec 2023 11:35:00 +0000 (12:35 +0100)]
cmake : target windows 8 or above for prefetchVirtualMemory in llama-talk (#1617)
Since we use prefetchVirtualMemory we specify we target win 8 or above, otherwise other compilers will refuse to use the prefetchVirtualMemory api, (I understand you are loading it dynamically but the header definition has this limitation)
Kreijstal [Sun, 10 Dec 2023 17:47:52 +0000 (18:47 +0100)]
cmake : Fix bug in httplib.h for mingw (#1615)
Fix bug in httlib.h for mingw, please see https://github.com/yhirose/cpp-httplib/issues/1669
Finn Voorhees [Fri, 8 Dec 2023 11:50:50 +0000 (11:50 +0000)]
metal : fix `ggml_metal_log` vargs (#1606)
Georgi Gerganov [Fri, 8 Dec 2023 11:43:37 +0000 (13:43 +0200)]
whisper.objc : disable timestamps for real-time transcription
Georgi Gerganov [Fri, 8 Dec 2023 11:43:03 +0000 (13:43 +0200)]
whisper : more debug messages + fix fallback logic
Georgi Gerganov [Fri, 8 Dec 2023 11:39:32 +0000 (13:39 +0200)]
metal : fix soft_max kernel src1 argument (#1602)
Georgi Gerganov [Thu, 7 Dec 2023 20:27:19 +0000 (22:27 +0200)]
sync : ggml (new ops, new backend, etc) (#1602)
* sync : ggml (new ops, new backend, etc)
* whisper : remove obsolete broadcasting code
* ggml : remove backend self-registers + fix ggml_concat + n_task logic
* metal : fix assert
* metal : print resource path
* whisper : fix bug if metal init fails
Oleg Sidorov [Tue, 5 Dec 2023 21:01:45 +0000 (22:01 +0100)]
server : pass max-len argument to the server (#1574)
This commit fixes the missing parameter binding for max-len between the input
arguments and wparams.
Finn Voorhees [Tue, 5 Dec 2023 01:14:26 +0000 (01:14 +0000)]
ios : Remove `#if arch(arm)` check for using Metal (#1561)