Commit Graph

169 Commits

Author SHA1 Message Date
Max Krasnyansky
0226613853
threadpool : skip polling for unused threads (#9461)
* threadpool: skip polling for unused threads

Currently all threads do N polling rounds even if only 1 thread is active (n_threads_cur == 1).
This commit adds a check to skip the polling for unused threads (ith >= n_threads_cur).

n_threads_cur is now an atomic_int to explicitly tell thread sanitizer that it is written
from one thread and read from other threads (not a race conditions).

* threadpool: further simplify and improve ggml_barrier

Avoid using strict memory order while polling, yet make sure that all threads go through
full memory barrier (memory fence) on ggml_barrier entrace and exit.

* threads: add simple barrier test

This test does lots of small, parallel matmul ops where the barriers in between dominate the overhead.

* threadpool: improve thread sync for new-graphs

Using the same tricks as ggml_barrier. All the polling is done with relaxed memory order
to keep it efficient, once the new graph is detected we do full fence using read-modify-write
with strict memory order.

* threadpool: improve abort handling

Do not use threadpool->ec (exit code) to decide whether to exit the compute loop.
threadpool->ec is not atomic which makes thread-sanitizer rightfully unhappy about it.

Instead introduce atomic threadpool->abort flag used for this. This is consistent with
how we handle threadpool->stop or pause.

While at it add an explicit atomic_load for n_threads_cur for consistency.

* test-barrier: release threadpool before releasing the context

fixes use-after-free detected by gcc thread-sanitizer on x86-64
for some reason llvm sanitizer is not detecting this issue.
2024-09-17 11:19:46 +03:00
slaren
23e0d70bac
ggml : move common CPU backend impl to new header (#9509)
Some checks are pending
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-cuda.Dockerfile platforms:linux/amd64 tag:full-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full.Dockerfile platforms:linux/amd64,linux/arm64 tag:full]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-cuda.Dockerfile platforms:linux/amd64 tag:light-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-intel.Dockerfile platforms:linux/amd64 tag:light-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli.Dockerfile platforms:linux/amd64,linux/arm64 tag:light]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-cuda.Dockerfile platforms:linux/amd64 tag:server-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-intel.Dockerfile platforms:linux/amd64 tag:server-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server.Dockerfile platforms:linux/amd64,linux/arm64 tag:server]) (push) Waiting to run
Nix CI / nix-eval (macos-latest) (push) Waiting to run
Nix CI / nix-eval (ubuntu-latest) (push) Waiting to run
Nix CI / nix-build (macos-latest) (push) Waiting to run
Nix CI / nix-build (ubuntu-latest) (push) Waiting to run
flake8 Lint / Lint (push) Waiting to run
2024-09-16 16:22:07 +02:00
Michael Podvitskiy
a6a3a5c531
ggml : link MATH_LIBRARY not by its full path (#9339) 2024-09-16 14:06:50 +03:00
Georgi Gerganov
19514d632e
cmake : do not hide GGML options + rename option (#9465)
* cmake : do not hide GGML options

ggml-ci

* build : rename flag GGML_CUDA_USE_GRAPHS -> GGML_CUDA_GRAPHS

for consistency

ggml-ci
2024-09-16 10:27:50 +03:00
Eve
5c3d0f1824
ggml : IQ4_NL sgemm + Q4_0 AVX optimization (#9422)
* squashed

readd my iq4_nl sgemm PR https://github.com/ggerganov/llama.cpp/pull/8049

have ggml_vec_dot_q4_0 do two blocks per loop for avx

try out f16c ggml_vec_dot_iq4_nl, but it's not really faster. as per https://github.com/ggerganov/llama.cpp/pull/8549 we can calculate several blocks at a time with no issue

* shuffle

* remove f16c iq4_nl as i cant make it faster than before
2024-09-16 09:48:24 +03:00
Georgi Gerganov
c4965a64f7
metal : handle zero-sized allocs (#9466) 2024-09-16 09:05:56 +03:00
Georgi Gerganov
6262d13e0b
common : reimplement logging (#9418)
Some checks are pending
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-cuda.Dockerfile platforms:linux/amd64 tag:full-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full.Dockerfile platforms:linux/amd64,linux/arm64 tag:full]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-cuda.Dockerfile platforms:linux/amd64 tag:light-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-intel.Dockerfile platforms:linux/amd64 tag:light-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli.Dockerfile platforms:linux/amd64,linux/arm64 tag:light]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-cuda.Dockerfile platforms:linux/amd64 tag:server-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-intel.Dockerfile platforms:linux/amd64 tag:server-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server.Dockerfile platforms:linux/amd64,linux/arm64 tag:server]) (push) Waiting to run
Nix CI / nix-eval (macos-latest) (push) Waiting to run
Nix CI / nix-eval (ubuntu-latest) (push) Waiting to run
Nix CI / nix-build (macos-latest) (push) Waiting to run
Nix CI / nix-build (ubuntu-latest) (push) Waiting to run
flake8 Lint / Lint (push) Waiting to run
Python Type-Check / pyright type-check (push) Waiting to run
https://github.com/ggerganov/llama.cpp/pull/9418
2024-09-15 20:46:12 +03:00
Michael Podvitskiy
6988da94a2
cmake : correct order of sycl flags (#9497) 2024-09-15 19:55:52 +03:00
Michael Podvitskiy
7596487beb
cmake : try to fix sycl+intel build (#9487) 2024-09-15 10:06:38 +03:00
Yuri Khrustalev
822b6322de
ggml : ggml_type_name return "NONE" for invalid values (#9458)
Some checks failed
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-cuda.Dockerfile platforms:linux/amd64 tag:full-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full.Dockerfile platforms:linux/amd64,linux/arm64 tag:full]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-cuda.Dockerfile platforms:linux/amd64 tag:light-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-intel.Dockerfile platforms:linux/amd64 tag:light-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli.Dockerfile platforms:linux/amd64,linux/arm64 tag:light]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-cuda.Dockerfile platforms:linux/amd64 tag:server-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-intel.Dockerfile platforms:linux/amd64 tag:server-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server.Dockerfile platforms:linux/amd64,linux/arm64 tag:server]) (push) Waiting to run
Nix CI / nix-eval (macos-latest) (push) Waiting to run
Nix CI / nix-eval (ubuntu-latest) (push) Waiting to run
Nix CI / nix-build (macos-latest) (push) Waiting to run
Nix CI / nix-build (ubuntu-latest) (push) Waiting to run
flake8 Lint / Lint (push) Waiting to run
Python Type-Check / pyright type-check (push) Waiting to run
update-flake-lock / lockfile (push) Has been cancelled
When running on Windows, the quantization utility attempts to print the types that are not set which leads to a crash.
2024-09-14 12:54:37 +03:00
Georgi Gerganov
1f4111e540
cmake : use list(APPEND ...) instead of set() + dedup linker (#9463)
Some checks are pending
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-cuda.Dockerfile platforms:linux/amd64 tag:full-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full.Dockerfile platforms:linux/amd64,linux/arm64 tag:full]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-cuda.Dockerfile platforms:linux/amd64 tag:light-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-intel.Dockerfile platforms:linux/amd64 tag:light-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli.Dockerfile platforms:linux/amd64,linux/arm64 tag:light]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-cuda.Dockerfile platforms:linux/amd64 tag:server-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-intel.Dockerfile platforms:linux/amd64 tag:server-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server.Dockerfile platforms:linux/amd64,linux/arm64 tag:server]) (push) Waiting to run
Nix CI / nix-eval (macos-latest) (push) Waiting to run
Nix CI / nix-eval (ubuntu-latest) (push) Waiting to run
Nix CI / nix-build (macos-latest) (push) Waiting to run
Nix CI / nix-build (ubuntu-latest) (push) Waiting to run
flake8 Lint / Lint (push) Waiting to run
* cmake : use list(APPEND ...) instead of set() + dedup linker

ggml-ci

* cmake : try fix sycl

* cmake : try to fix sycl 2

* cmake : fix sycl build (#9469)

* try fix sycl build

* use CMAKE_CXX_FLAGS as a string variable

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* one more CMAKE_CXX_FLAGS fix (#9471)

---------

Co-authored-by: Michael Podvitskiy <podvitskiymichael@gmail.com>
2024-09-14 10:55:05 +03:00
Dou Xinpeng
e6b7801bd1
cann: Add host buffer type for Ascend NPU (#9406)
Some checks failed
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-cuda.Dockerfile platforms:linux/amd64 tag:full-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full.Dockerfile platforms:linux/amd64,linux/arm64 tag:full]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-cuda.Dockerfile platforms:linux/amd64 tag:light-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-intel.Dockerfile platforms:linux/amd64 tag:light-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli.Dockerfile platforms:linux/amd64,linux/arm64 tag:light]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-cuda.Dockerfile platforms:linux/amd64 tag:server-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-intel.Dockerfile platforms:linux/amd64 tag:server-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server.Dockerfile platforms:linux/amd64,linux/arm64 tag:server]) (push) Waiting to run
Nix CI / nix-eval (macos-latest) (push) Waiting to run
Nix CI / nix-eval (ubuntu-latest) (push) Waiting to run
Nix CI / nix-build (macos-latest) (push) Waiting to run
Nix CI / nix-build (ubuntu-latest) (push) Waiting to run
flake8 Lint / Lint (push) Waiting to run
Python Type-Check / pyright type-check (push) Waiting to run
Python check requirements.txt / check-requirements (push) Has been cancelled
* feat: Add host buffer type for Ascend NPU(CANN backend)

* fix some checking errors

* Add a few comments
2024-09-12 19:46:43 +08:00
Ahmad Tameem
2b00fa7997
riscv : modify Makefile and add a RISCV_VECT to print log info (#9442)
- Added ggml_cpu_has_riscv_v() in GGML to print system info in log
- Modified Makefile to only use flag when cross compiling for RISC-V
2024-09-12 14:24:31 +03:00
Georgi Gerganov
d6a04f872d
ggml : hide ggml_object, ggml_cgraph, ggml_hash_set (#9408)
* ggml : hide ggml_object, ggml_cgraph, ggml_hash_set

ggml-ci

* ggml : add ggml-impl.h to backends

* ggml : fix compiler warnings

ggml-ci

* ggml : add assert upon adding nodes
2024-09-12 14:23:49 +03:00
Xinpeng Dou
df4b7945ae
cann: Fix error when running a non-exist op (#9424)
Some checks are pending
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-cuda.Dockerfile platforms:linux/amd64 tag:full-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full.Dockerfile platforms:linux/amd64,linux/arm64 tag:full]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-cuda.Dockerfile platforms:linux/amd64 tag:light-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-intel.Dockerfile platforms:linux/amd64 tag:light-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli.Dockerfile platforms:linux/amd64,linux/arm64 tag:light]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-cuda.Dockerfile platforms:linux/amd64 tag:server-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-intel.Dockerfile platforms:linux/amd64 tag:server-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server.Dockerfile platforms:linux/amd64,linux/arm64 tag:server]) (push) Waiting to run
Nix CI / nix-eval (macos-latest) (push) Waiting to run
Nix CI / nix-eval (ubuntu-latest) (push) Waiting to run
Nix CI / nix-build (macos-latest) (push) Waiting to run
Nix CI / nix-build (ubuntu-latest) (push) Waiting to run
flake8 Lint / Lint (push) Waiting to run
2024-09-12 09:02:35 +08:00
Johannes Gäßler
5af118efda
CUDA: fix --split-mode row race condition (#9413) 2024-09-11 10:22:40 +02:00
R0CKSTAR
b34e023480
musa: remove Clang builtins mapping (#9421)
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
2024-09-11 03:46:55 +02:00
Alberto Cabrera Pérez
51b6038636
sycl : update support conditions (#9394)
* sycl : update support condition to im2col

Signed-off-by: Alberto Cabrera <alberto.cabrera@codeplay.com>

* Added TODO to remind supporting FP32 im2col

---------

Signed-off-by: Alberto Cabrera <alberto.cabrera@codeplay.com>
2024-09-11 08:53:42 +08:00
Georgi Gerganov
00ba2ff781
metal : fix compile warning with GGML_METAL_NDEBUG (#0) 2024-09-10 10:17:43 +03:00
Radoslav Gerganov
293bebe077
rpc : fix segfault with nkvo (#9389)
* rpc : fix nkvo

* rpc : buf_size must not be static

ref: #9337

---------

Co-authored-by: slaren <slarengh@gmail.com>
2024-09-09 18:40:10 +03:00
Prashant Vithule
5fac4d5764
ggml : vector length agnostic SVE support (#9290)
* Implemented vector length agnostic SVE using switch case for 512-bit, 256-bit, 128-bit vector lengths

* Implemented vector length agnostic SVE using switch case for 512-bit, 256-bit, 128-bit vector lengths

* Removed WhiteSpaces

* ggml : style changes + fix 512-bit nb loop check

- fix local scope in switch cases
- consistent predicate names
- empty lines when necessary
- opening braces, spaces
- const-correctness
- add asserts

* Update ggml/src/ggml-quants.c

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-09-09 18:37:18 +03:00
Johannes Gäßler
8e6e2fbe14
CUDA: fix variable name conflict for Windows build (#9382) 2024-09-09 14:22:53 +02:00
Markus Tavenrath
daa9623ab0
Overlap cmdbuffer creation and cmdbuffer execution in Vulkan backend by submitting smaller cmdbuffers early. (#9118)
* Overlap cmdbuffer creation and cmdbuffer execution in Vulkan backend by submitting smaller cmdbuffers early.

* fix compile issues

* Fix issues where the last submit wasn't executed or handled properly.

* remove trailing whitespace

* Repair GGML_VULKAN_CHECK_RESULTS

* Increase submit counter only if actual work has been submitted and increase submit count to 100.

* Fix some nodes are not checked with GGML_VULKAN_CHECK_RESULTS enabled.
2024-09-08 21:43:48 +02:00
Georgi Gerganov
e079bffb66
cuda : fix FA Q src index (1 -> 0) (#9374) 2024-09-08 22:01:02 +03:00
Neo Zhang Jianyu
2a358fb0c4
[SYCL] add check malloc result on device (#9346)
* add check malloc result on device

* update for review comments, check all malloc_device() result

---------

Co-authored-by: arthw <14088817+arthw@users.noreply.github.com>
2024-09-08 19:05:29 +08:00
Georgi Gerganov
a876861455 metal : update support condition for im2col + fix warning (#0) 2024-09-08 11:05:55 +03:00
Salvatore Mesoraca
406c1a32a1 vulkan: add dryrun support to sin and cos ops (ggml/947)
sin and cos failed test-backend-ops because they
tried to dereference a context pointer that is null
on dry runs.

This commit prevents that segfault.

Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com>
2024-09-08 11:05:55 +03:00
Salvatore Mesoraca
9cb9260861 vulkan: correctly report support for OP_CONT (ggml/946)
test-backend-ops fails because ggml_cont aborts
when invoked passing an unsupported type.

This commit makes ggml_cont tests pass

Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com>
2024-09-08 11:05:55 +03:00
Johannes Gäßler
202084d31d tests: add gradient tests for all backends (ggml/932)
* tests: add gradient checking to test-backend-ops

* remove old comment

* reorder includes

* adjust SIN/COS parameters

* add documentation, use supports_op if possible
2024-09-08 11:05:55 +03:00
Johannes Gäßler
dbbebcab33 ggml: fix ggml_graph_cpy undefined behavior (ggml/943) 2024-09-08 11:05:55 +03:00
Georgi Gerganov
ba1cf846ed cann : fix doxy (ggml/0) 2024-09-08 11:05:55 +03:00
Mengqing Cao
d2d3200b38 cann : add Ascend NPU support (whisper/2336)
* enable Ascend NPU in src/whisper.cpp
  * sync test-backend-ops with llama.cpp
2024-09-08 11:05:55 +03:00
Georgi Gerganov
51d964a4ef cuda : mark BF16 CONT as unsupported 2024-09-08 11:05:55 +03:00
Salvatore Mesoraca
efe6a83e30 ggml : fix cont with transposed tensors when one dimension is 1 (ggml/934)
* ggml_cont: fix issue with transposed tensors when one dimension is 1

when using multiple threads, it is not enough
to check for the tensors to be contiguous for
ggml_compute_forward_dup_same_cont to work correctly.
The tensors strides also need to match.

Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com>

* Add ggml_cont tests

Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com>

* Remove dead code

it isn't possible to reach this code because
all these functions are invoked by ggml_compute_forward_dup
if and only if src0->type != dst->type

Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com>

* Make ggml_compute_forward_dup_same_cont work with contiguous tensors

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com>

---------

Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-09-08 11:05:55 +03:00
Eve
e536426ded
llamafile : disable sgemm for batch-size 1 (#9330) 2024-09-07 22:02:26 +03:00
slaren
e32d0816ed
ggml : always check bounds on get_rows operations (#9354) 2024-09-07 20:23:07 +02:00
Xuan Son Nguyen
947538acb8
ggml : fix missing cpu_set_t on emscripten (#9336)
* ggml : fix missing cpu_set_t on emscripten

* better version

* bring back android part
2024-09-07 12:01:34 +02:00
Changyeon Kim
409dc4f8bb
ggml : fix build break for the vulkan-debug (#9265)
- windows build : Ok.
- linux build : Ok.

Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>
2024-09-06 15:54:50 +03:00
Markus Tavenrath
8ebe8ddebd
Improve Vulkan shader build system (#9239)
* Improve Vulkan shader builds system

- Add dependency to vulkan-shaders-gen to rebuild shaders when changing the shader compilation utility.
- Add option to generate debug info for Vulkan shaders to provide shader source to Vulkan shader profiling tools

* remove not required self dependency
2024-09-06 08:56:17 +02:00
compilade
9bc6db28d0
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
* ggml-quants : 1.625 bpw ternary packing for BitNet 1.58b

* ggml-quants : faster 1.625 bpw AVX2 vec_dot

Not using a lookup table anymore makes it match q4_0 speed.

* gguf-py : fix formatting

* llama : remove spaces on empty line

* ggml-quants : subtract 1 when back in epi8

This makes the 1.625 bpw type go faster than q4_0. Still not the fastest.

* ggml-quants : Q2_2 now faster than Q4_K on with AVX2

* ggml-quants : cleanup Q1_3 code formatting

* ggml-quants : ARM NEON vec_dot for q2_2 and q1_3

* ggml-quants : use ceiling division when quantizing q1_3

* convert-hf : simplify BitNet pre-quantization

This still results in the exact same tensor weights and scales,
but it reveals some weirdness in the current algorithm.

* convert-hf : allow converting the weird BitNet 1.3B

Its FFN size is 5460 which is not convenient.
The offending tensors are kept in F16,
which makes the final model 5.01 bpw.

* bitnet : replace 1.58b with b1.58, as in the paper

* ggml-quants : fix build failure on Windows

* ggml-quants : attempt to fix Arm 32-bit support

* ggml : add some informative comments in q1_3 vec_dot

* ggml : add TQ1_0 and TQ2_0 ternary quantization types

* ggml : even faster TQ2_0

* ggml : also faster TQ1_0

Same optimization as for TQ2_0 by offsetting the sum instead of the weights.
This makes TQ1_0 almost as fast as Q8_0 on AVX2.

* ggml : fix build issues in certain environments

* ggml : add NEON vec_dot implementation for TQ1_0 and TQ2_0

* ggml : avoid directly using vmlal_high_s8, for 32-bit ARM compat

The compiler seems smart enough to use the same instruction
even when using vget_high_s8 instead.

* ggml : remove q1_3 and q2_2

No more 1.625 bpw and 2.000 bpw,
now instead using 1.6875 bpw and 2.0625 bpw
with TQ1_0 and TQ2_0, respectively.

* llama : remove the separate scale tensors of BitNet b1.58

They won't be needed, since the remaining ternary quant types have
built-in scales.

* ggml-quants : rename fields of TQ1_0 and TQ2_0 structs for consistency

* ggml-quants : allow using vdotq_s32 in TQ2_0 vec_dot

Not yet tested on hardware which supports it,
might not work or might not even compile. But also it might.
It should make the performance better on recent ARM CPUs.

* ggml-quants : remove comment about possible format change of TQ2_0

Making it slightly more convenient for AVX512
but less convenient for everything else is not worth the trouble.

* gguf-py : Numpy (de)quantization for TQ1_0 and TQ2_0

* ggml-quants : use roundf instead of nearest_int for TQ1_0 and TQ2_0

This does not change anything for ternary models,
since their values should never end up being in halfway cases anyway.

* convert : allow direct conversion to TQ1_0 and TQ2_0

The token embeddings and output tensors are kept in F16
to allow quantizing them to Q4_K and Q6_K with llama-quantize.

* llama : handle fallback for TQ1_0 and TQ2_0 with Q4_0

Q4_0 is not completely symmetric (so not lossless for ternary models),
but it should be good enough.

* ggml-quants : allow using ARM dot product instructions for TQ1_0

* ggml-quants : deduplicate TQ1_0 and TQ2_0 __ARM_FEATURE_DOTPROD support

* ggml : remove unused ggml_mul special case

It would otherwise conflict with the more general
optimization coming with Mamba-2.

* ggml : handle TQ1_0 and TQ2_0 in dequantization-based operators

* test-backend-ops : add TQ1_0 and TQ2_0 comments for later

Not yet adding uncommented, because some backends like SYCL and Metal
do not properly handle unknown types in supports_op for GGML_OP_MUL_MAT.
(and Metal also doesn't handle it with GGML_OP_GET_ROWS)
Support for TQ1_0 and TQ2_0 for other backends than CPU
will be added in follow-up pull requests.
2024-09-05 21:48:47 -04:00
slaren
4db04784f9
cuda : fix defrag with quantized KV (#9319) 2024-09-05 11:13:11 +02:00
Srihari-mcw
581c305186
ggml : AVX2 support for Q4_0_8_8 (#8713)
* Add AVX2 based implementations for quantize_q8_0_4x8, ggml_gemv_q4_0_8x8_q8_0 and ggml_gemm_q4_0_8x8_q8_0 functions

* Update code to fix issues occuring due to non alignment of elements to be processed as multiple of 16 in MSVC

* Update comments and indentation

* Make updates to reduce number of load instructions
2024-09-04 19:51:22 +03:00
Ouadie EL FAROUKI
5910ea9427
[SYCL] Fix DMMV dequantization (#9279)
Fixed dmmv dequant for ncols== GGML_SYCL_DMMV_X
2024-09-04 16:26:33 +01:00
yuri@FreeBSD
f771d064a9
ggml : add pthread includes on FreeBSD (#9258) 2024-09-02 18:25:30 +03:00
Molly Sophia
8f1d81a0b6
llama : support RWKV v6 models (#8980)
* convert_hf_to_gguf: Add support for RWKV v6

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Add RWKV tokenization

* Fix build

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Do not use special tokens when matching in RWKV tokenizer

* Fix model loading

* Add (broken) placeholder graph builder for RWKV

* Add workaround for kv cache

* Add logits conversion to rwkv5

* Add rwkv5 layer norms

* Add time mix KVRG & correct merge mistake

* Add remaining time mix parameters

* Add time mix output loading

* Add placeholder llm_build_time_mix

* Fix build

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Load more tensors for rwkv v6

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Fix rwkv tokenizer

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* ggml: Add unary operator Exp

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* RWKV v6 graph building

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Add ``rescale_every_n_layers`` parameter

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Add ``wkv.head_size`` key for RWKV

so it doesn't reuse Mamba ssm parameters

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Fix offloading layers to CUDA

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Fix parallel inferencing for RWKV

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Remove trailing whitespaces

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* build_rwkv: Avoid using inplace operations

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* convert_hf_to_gguf: rwkv: Avoid using ``eval``

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* convert_hf_to_gguf: rwkv tokenizer: Don't escape sequences manually

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Update convert_hf_to_gguf.py

Co-authored-by: compilade <git@compilade.net>

* ggml: Add backward computation for unary op ``exp``

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Update convert_hf_to_gguf.py

Co-authored-by: compilade <git@compilade.net>

* Update convert_hf_to_gguf.py

Co-authored-by: compilade <git@compilade.net>

* Use MODEL_ARCH.RWKV6 instead of MODEL_ARCH.RWKV

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* build_rwkv6: Simplify graph

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* llama: rwkv6: Detect model.type

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* llama: rwkv6: Fix tensor loading for 7B/14B models

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* llama: rwkv6: Fix group_norm assertion failure with Metal

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* llama: rwkv6: Clean up

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* llama: rwkv6: Add quantization tensor exclusion

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* llama: rwkv6: Use the new advanced batch splits

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Update src/llama.cpp

Co-authored-by: compilade <git@compilade.net>

* llama: rwkv6: Use ``ggml_norm`` instead of ``ggml_group_norm``

Co-authored-by: compilade <git@compilade.net>

* llama: rwkv6: Apply code style and misc changes

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* converter: Use class name ``Rwkv6Model``

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* llama: rwkv6: Make use of key ``feed_forward_length``

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* llama: rwkv6: Add kv ``time_mix_extra_dim`` and ``time_decay_extra_dim``

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* converter: Match ``new_name`` instead of ``name`` for float32 explicit tensors

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* llama: rwkv6: Keep ``time_mix_w1/w2`` as F32

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* llama: rwkv6: Remove unused nodes

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* llama: rwkv6: Apply code format changes

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* llama: rwkv6: Add lora for some supported tensors

Currently att.key/receptance/value/gate/output, ffn.receptance/key/value, as well as head.weight

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* rwkv : speed-up tokenization using trie

* minor : style + indentation

* llama: rwkv6: Avoid division by zero

Co-authored-by: compilade <git@compilade.net>

* ggml: rwkv_wkv: Avoid copying the state

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

---------

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
Co-authored-by: Layl Bongers <3094382+LaylBongers@users.noreply.github.com>
Co-authored-by: compilade <git@compilade.net>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-09-01 17:38:17 +03:00
Srihari-mcw
ea5d7478b1
sgemm : improved Q4_0 and Q8_0 performance via 4xN and Mx4 gemm (#8908) 2024-08-31 11:20:35 +03:00
Faisal Zaghloul
42c76d1358
Threadpool: take 2 (#8672)
* Introduce ggml_compute_threadpool

- OpenMP functional: check
- Vanilla ggml functional: Check
- ggml w/threadpool functional: Check
- OpenMP no regression: No glaring problems
- Vanilla ggml no regression: No glaring problems
- ggml w/threadpool no regression: No glaring problems

* Minor fixes

* fixed use after release bug

* fixed a harmless race condition

* Fix Android bulid issue

* fix more race conditions

* fix deadlock for cases where cgraph.n_nodes == 1

and fix --poll case

* threadpool: use cpu_get_num_math to set the default number of threadpool threads

This way we avoid using E-Cores and Hyperthreaded siblings.

* bench: create fresh threadpool for each test

For benchmarking it's better to start a fresh pool for each test with the exact number of threads
needed for that test. Having larger pools is suboptimal (causes more load, etc).

* atomics: always use stdatomics with clang and use relaxed memory order when polling in ggml_barrier

This also removes sched_yield() calls from ggml_barrier() to match OpenMP behavior.

* threadpool: make polling the default to match openmp behavior

All command line args now allow for setting poll to 0 (false).

* threadpool: do not wakeup threads in already paused threadpool

* fix potential race condition in check_for_work

* threadpool: do not create two threadpools if their params are identical

* threadpool: reduce pause/resume/wakeup overhead in common cases

We now start threadpool in paused state only if we have two.
The resume is now implicit (ie new work) which allows for reduced locking and context-switch overhead.

* threadpool: add support for hybrid polling

poll params (--poll, ...) now specify "polling level", i.e. how aggresively we poll before waiting on cond.var.
poll=0 means no polling, 1 means poll for 128K rounds then wait, 2 for 256K rounds, ...

The default value of 50 (ie 50x128K rounds) seems like a decent default across modern platforms.
We can tune this further as things evolve.

* threadpool: reduce the number of barrier required

New work is now indicated with an atomic counter that is incremented for
each new graph that needs to be computed.
This removes the need for extra barrier for clearing the "new_work" and
removes the special case for trivial graphs.

* threadpool: remove special-casing for disposable threadpools

With the efficient hybrid polling there is no need to make disposable pools any different.
This simplifies the overall logic and reduces branching.

Include n_threads in debug print for disposable threadpool.

Declare pause and stop flags as atomic_bool
This doesn't actually generate any memory barriers and simply informs
the thread sanitizer that these flags can be written & read by different
threads without locking.

* threadpool: do not clear barrier counters between graphs computes (fixes race with small graphs)

This fixes the race condition with very small graphs where the main thread happens to
start a new graph while the workers are just about to exit from barriers.

* threadpool: use relaxed order for chunk sync

Full memory barrier is an overkill for this since each thread works on different chunk

* threadpool: remove abort_callback from threadpool state

* threadpool: better naming for thread/cpumask releated functions

* threadpool: consistent use of int type for n_threads params

* threadpool: add support for ggml_threadpool_params_default/init

Also removes the need for explicit mask_specified param.
all-zero cpumask means use default (usually inherited) cpu affinity mask.

* threadpool: move typedef into ggml.h

* threadpool: fix apply_priority() function name

* threadpool: fix swift wrapper errors due to n_threads int type cleanup

* threadpool: enable --cpu-mask and other threadpool related options only if threadpool is enabled

* threadpool: replace checks for compute_thread ret code with proper status check

* threadpool: simplify threadpool init logic and fix main thread affinity application

Most of the init code is now exactly the same between threadpool and openmp.

* threadpool: update threadpool resume/pause function names

* threadpool: enable openmp by default for now

* threadpool: don't forget to free workers state when omp is enabled

* threadpool: avoid updating process priority on the platforms that do not require it

On Windows we need to change overall process priority class in order to set thread priorities,
but on Linux, Mac, etc we do not need to touch the overall process settings.

* threadpool: update calling thread prio and affinity only at start/resume

This avoids extra syscalls for each graph_compute()

* llama-bench: turn threadpool params into vectors, add output headers, etc

* llama-bench: add support for cool off between tests --delay

This helps for long running tests on platforms that are thermally limited (phones, laptops, etc).
--delay (disabled by default) introduces the sleep for N seconds before starting each test.

* threadpool: move process priority setting into the apps (bench and cli)

This avoids changing the overall process priority on Windows for the apps
that use ggml/llama.cpp directy.

* threadpool: move all pause/resume logic into ggml

* threadpool: futher api cleanup and prep for future refactoring

All threadpool related functions and structs use ggml_threadpool prefix.

* threadpool: minor indent fixes

* threadpool: improve setprioty error message

* Update examples/llama-bench/llama-bench.cpp

Co-authored-by: slaren <slarengh@gmail.com>

* threadpool: fix indent in set_threadpool call

* use int32_t for n_thread type in public llama.cpp API

* threadpool: use _new and _free instead of _create and _release

* fix two more public APIs to use int32_t for n_threads

* build: set _GNU_SOURCE for Adroid

---------

Co-authored-by: Max Krasnyansky <quic_maxk@quicinc.com>
Co-authored-by: fmz <quic_fzaghlou@quic.com>
Co-authored-by: Max Krasnyansky <max.krasnyansky@gmail.com>
Co-authored-by: slaren <slarengh@gmail.com>
2024-08-30 01:20:53 +02:00
Georgi Gerganov
20f1789dfb vulkan : fix build (#0)
ggml-ci
2024-08-27 22:41:27 +03:00
Georgi Gerganov
231cff5f6f sync : ggml 2024-08-27 22:41:27 +03:00
slaren
7d787ed96c
ggml : do not crash when quantizing q4_x_x with an imatrix (#9192) 2024-08-26 19:44:43 +02:00